2023Activity reportProject-TeamNEO

6.1.1 marmote

• Name:
  MARkovian MOdeling: The Environment
• Keyword:
  Markov model
• Functional Description:

  marmote is a C++ library for modeling with Markov chains. It consists in a reduced set of high-level abstractions for constructing state spaces, transition structures and Markov chains (discrete-time and continuous-time). It provides the ability of constructing hierarchies of Markov models, from the most general to the particular, and equip each level with specifically optimized solution methods. The current release features the library marmoteMDP for modeling Markov Decision Processes and solving them.

  This software was started within the ANR MARMOTE project: ANR-12-MONU-00019 under the name marmoteCore. Within the marmote project, the code conforms the latest C++ standards and the library is available on multiple platforms via a conda distribution.

• Release Contributions:
  This version improves the code portability and its conformity to recent C++ standards. It contains the first release of marmoteMDP, a library for manipulating Markov Decision Processes, built on top of marmote's core. It also provides for the first time a complete documentation for installing and using the library, as well as numerous examples.
• News of the Year:
  The first public release of marmote occured in May 2023 with version 0.2.0. The release featured, for the first time, installation procedures on multiple architectures, a documentation and numerous examples. It also featured the library marmoteMDP, built on top of marmote's core, devoted to the modeling and solution of Markov Decision Processes.
• URL:
  https://­marmote.­gitlabpages.­inria.­fr/­marmote/
• Publications:
  hal-03770430v1, hal-03781620v1, hal-02395100v1, hal-04176076v1
• Contact:
  Alain Jean-Marie
• Participants:
  Alain Jean-Marie, Patrick Brown, Emmanuel Hyon
• Partner:
  Université Paris Nanterre

7.1.1 Games with Commitments and Noisy Observations

In 56, S. Perlaza, A. Jean-Marie and K. Sun studied classical zero-sum games under the following assumptions: $\left(1\right)$ One of the players (the leader) commits to choose its actions by sampling a given probability measure (strategy); $\left(2\right)$ The leader announces its action, which is observed by its opponent (the follower) through a binary channel; and $\left(3\right)$ the follower chooses its strategy based on the knowledge of the leader's strategy and the noisy observation of the leader's action. Under these conditions, the equilibrium is shown to always exist. Interestingly, even subject to noise, observing the actions of the leader is shown to be either beneficial or immaterial for the follower. More specifically, the payoff at the equilibrium of this game is upper bounded by the payoff at the Stackelberg equilibrium (SE) in pure strategies; and lower bounded by the payoff at the Nash equilibrium, which is equivalent to the SE in mixed strategies. Finally, necessary and sufficient conditions for observing the payoff at equilibrium to be equal to its lower bound are presented. Sufficient conditions for the payoff at equilibrium to be equal to its upper bound are also presented. This work was presented as a conference in 41.

S. Perlaza, A. Jean-Marie, and E. Athanasakos are currently extending these results to more general classes of channels. In particular, Gaussian channels.

7.1.2 Pricing Strategies for Digital Renting Platforms

In 54, E. Altman, S. Perlaza, and A. Krishnan K.S. considered different pricing models for a platform-based rental system, such as Airbnb. A linear model is assumed for the demand response to price, and existence and uniqueness conditions for Nash equilibria are obtained. The Stackelberg equilibrium prices for the game are also obtained, and an iterative scheme is provided, which converges to the Nash equilibrium. Different cooperative pricing schemes are studied, and splitting of revenues based on the Shapley value is discussed. It is shown that a division of revenue based on the Shapley value gives a revenue to the platform proportional to its control of the market. The demand response function is modified to include user response to quality of service. It is shown that when the cost to provide quality of service is low, both renter and the platform will agree to maximize the quality of service. However, if this cost is high, they may not always be able to agree on what quality of service to provide. This work was presented as a conference in 32.

7.1.3 Constrained games in energy markets

In 42 R. Taisant (INOCS), M. Datar, H. Le Cadre (INOCS), and E. Altman consider a peer-to-peer electricity market modeled as a network game, where End Users (EUs) minimize their cost by computing their demand and generation while satisfying a set of local and coupling constraints. The nominal demand of EUs constitutes sensitive information, that EUs might want to keep private. The authors of 42 prove that the network game admits a unique Variational Equilibrium, which depends on the private information of all the EUs. A data aggregator is introduced, which aims to learn the EUs’ private information. The EUs might have incentives to report biased and noisy readings to preserve their privacy, which creates shifts in their strategies. Relying on performative prediction, the authors define a decision-dependent game G${}^{\mathrm{stoch}}$ to couple the network game with a data market. Two variants of the Repeated Stochastic Gradient Method (RSGM) are proposed to compute the Performatively Stable Equilibrium solution of G${}^{\mathrm{stoch}}$, that outperform RSGM with respect to efficiency gap minimization, privacy preservation, and convergence rates in numerical simulations. This work has been extended in 55 by H. Le Cadre and M. Guckert (INOCS), M. Datar and E. Altman (also LIA).

7.2.1 Retrial Queues

In 13 K. Avrachenkov in collaboration with E. Morozov and R. Nekrasova (Karelian Institute of Applied Mathematical Research, Russia) establish stability criterion for a two-class retrial system with Poisson inputs, general class-dependent service times and class-dependent constant retrial rates. They also characterize an interesting phenomenon of partial stability when one orbit is tight but the other orbit goes to infinity in probability. All theoretical results are illustrated by numerical experiments.

7.2.2 Spatial Queues with Nearest Neighbor Shifts

Motivated primarily by electric vehicles (EV) queueing at charging stations, B.R. Vinay Kumar studies multiple server queues on an Euclidean space. He considers $N$ servers that are distributed uniformly in ${[0,1]}^d$. Customers or EV users arrive at the servers according to Poisson processes of intensity $\lambda$. However, they probabilistically decide whether to join the queue they arrived at, or move to one of the nearest neighbors. The strategy followed by the customers affects the load on the servers in the long run. In 43, 57, B.R. Vinay Kumar is interested in characterizing the fraction of servers that bear a larger load as compared to when the users do not follow any strategy, i.e., they join the queue at which they arrive. These are called overloaded servers. He evaluates the expected fraction of overloaded servers in the system for the one dimensional case ($d=1$) when the users follow probabilistic nearest neighbor shift strategies.

7.2.3 Performance Models for Similary Caching

Similarity caching allows requests for an item to be served by a similar item. Applications include recommendation systems, multimedia retrieval, and machine learning. Recently, many similarity caching policies have been proposed, like SIM-LRU (Similarity Least Recently Used) and its generalization RND-LRU (Random Least Recently Used), but the performance analysis of their hit ratio is still wanting. Y. Ben Mazziane, S. Alouf, and G. Neglia, together with D. S. Menasche (Federal Univ. of Rio de Janeiro, Brazil) are pursuing their effort to estimate the hit ratio of the similarity caching policy RND-LRU. They extend the popular time-to-live approximation in classic caching to similarity caching. They introduce the RND-TTL (Random Time-to-Live) approximation and the RND-TTL cache model and tune the model's parameters in such a way as to mimic the behavior of RND-LRU. The parameter tuning involves solving a fixed point system of equations for which they provide an algorithm for numerical resolution and sufficient conditions for its convergence.

7.2.4 Branching processes

In 17, R. Dhounchak and V. Kavitha (IIT Mumbai) in collaboration with E. Altman consider the inherent timeline structure of the appearance of content in online social networks (OSNs) while studying content propagation. They model the propagation of a post/content of interest by a multi-type branching process. The latter allows one to predict the emergence of global macro properties (e.g., the spread of a post in the network) from the laws and parameters that determine local interactions. The local interactions largely depend upon the timeline (an inverse stack capable of holding many posts and one dedicated to each user) structure and the number of friends (i.e., connections) of users, etc. They explore the use of multi-type branching processes to analyze the viral properties of the post, e.g., to derive the expected number of shares, the probability of virality of the content, etc. In OSNs, the new posts push down the existing contents in timelines, which can greatly influence content propagation; their analysis considers this influence. They find that one leads to draw incorrect conclusions when the timeline (TL) structure is ignored. One cannot capture some interesting paradigm shifts/phase transitions; for example, virality chances are not monotone with network activity parameter, as shown by analysis including TL influence.

7.3.1 Empirical Risk Minimization (ERM)

Classical problems such as classification, pattern recognition, regression, and density estimation can be posed as special cases of the ERM problem. Unfortunately, ERM is prone to training data memorization, a phenomenon also known as overfitting. For this reason, ERM is often regularized in order to provide generalization guarantees. That is, to identify models using available training datasets that induce low empirical risk with respect to unseen datasets. At Neo  special attention is payed to the study of the statistical properties of the solutions to ERM problems subject to particular regularizations. The main feature of this research effort is that contrary to the main stream in the community, this analysis is made for fixed training datasets, which provides new and insightful mathematical tools for the analysis of generalization capabilities of machine learning algorithms.

7.3.2 Characterization of the Generalization Error

The expected generalization error (GE) is a central performance metric for the analysis of generalization capabilities of machine learning algorithms. In a nutshell, the GE characterizes the ability of a learning algorithm to correctly find patterns in datasets that are not available during the training stage. Specifically, it is defined for a fixed training dataset and a specific model instance, as the difference between the population risk induced by the model and the empirical risk with respect to the training dataset. At Neo  our research focuses on the search of closed-form expressions of the GE for specific algorithms under the assumption that datasets follow a specific probability distribution that is consistent with the training dataset.

7.3.3 Online Learning

Online learning algorithms have been successfully used to design caching policies with regret guarantees. Existing algorithms assume that the cache knows the exact request sequence, but this may not be feasible in high load and/or memory-constrained scenarios, where the cache may have access only to sampled requests or to approximate requests' counters. In 27, Y. Ben Mazziane, F. Faticanti, G. Neglia, and S. Alouf propose the Noisy-Follow-the-Perturbed-Leader (NFPL) algorithm, a variant of the classic Follow-the-Perturbed-Leader (FPL) when request estimates are noisy, and they show that the proposed solution has sublinear regret under specific conditions on the requests estimator. The experimental evaluation compares the proposed solution against classic caching policies and validates the proposed approach under both synthetic and real request traces.

In 29, F. Faticanti and G. Neglia study a batched version of optimistic online algorithms for caching. The analysis consists of updating the cache state less frequently with respect to traditional caching algorithms that update the cache state after receiving every single new request. This new approach proposes to cumulate a batch of requests before updating the cache given the high computational complexity of online algorithms based on Follow-The-Regularized-Leader (FTRL). No-regret results are showed in this new setting and experimental results show that the batched versions of the online algorithms outperform traditional caching policies on both synthetic and real traces.

The abstract of the paper “Enabling Long-term Fairness in Dynamic Resource Allocation ” has been published in the Proceedings of the 2023 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems 40. The corresponding research activity is described in NEO activity report for 2022.

7.3.4 Reinforcement Learning

In 35 K. Avrachenkov in collaboration with T. Pagare and V. Borkar (IIT Bombay, India) extend the provably convergent Full Gradient DQN (Deep Q-Network) algorithm for discounted reward Markov decision processes from Avrachenkov et al. (2021) to average reward problems. They experimentally compare widely used RVI (Relative Value Iteration) Q-learning with recently proposed Differential Q-learning in the neural function approximation setting with Full Gradient DQN and DQN. They also extend this to learn Whittle indices for Markovian restless multi-armed bandits and observe a better convergence rate of the proposed Full Gradient variant across different tasks.

K. Avrachenkov in collaboration with V. Borkar and J. Nair (IIT Bombay, India) have organized and edited a special volume of Dynamic Games and Applications journal on the topic “Multi-Agent Dynamic Decision Making and Learning” 45. This field interests multiple communities such as dynamic games, control theory and machine learning, especially, reinforcement learning. 14 papers have been accepted and published in this special volume.

7.3.5 Federated Learning

In 37, A. Rodio, F. Faticanti, O. Marfoq, and G. Neglia in collaboration with E. Leonardi (Polytechnic Univ. of Turin, Italy) provide the first convergence result for Federated Learning algorithms under heterogeneous and correlated client availability. Their analysis shows the negative impact of correlation on the algorithms' convergence rate and highlights a trade-off between optimization error (related to convergence speed) and bias error (indicative of model quality). Their proposed Correlation-Aware FL (CA-Fed) algorithm effectively balances convergence speed and model quality by adjusting client aggregation weights and selectively excluding highly correlated, low-availability clients. Throughout simulations, CA-Fed achieves higher time-average accuracy and reduced standard deviation compared to existing methods on both synthetic and real datasets.

Subsequently, in 21, A. Rodio, F. Faticanti, O. Marfoq, and G. Neglia in collaboration with E. Leonardi (Polytechnic Univ. of Turin, Italy) further enhance their CA-Fed algorithm by introducing a new hyper-parameter to optimize the trade-off between convergence speed and model quality. A sensitivity analysis confirms this parameter's impact on convergence. In contrast to 37, which relied on prior knowledge of clients' availability and correlation, they propose a Bayesian estimator with a beta prior, requiring only a limited amount of observations to outperform existing methods. Additionally, they address a gap in 37 by evaluating CA-Fed in spatially correlated scenarios, where the availability patterns are correlated among clients.

In 38, A. Rodio and G. Neglia in collaboration with F. Busacca and S. Palazzo (Univ. of Catania, Italy), S. Mangione and I. Tinnirello (Univ. of Palermo, Italy), and F. Restuccia (Northeastern Univ., USA) address training Federated Learning algorithms in wireless networks with packet losses. Contrary to conventional approaches that focus on mitigating packet losses through retransmission or error correction, they show that FL algorithms can effectively learn in asymmetric lossy channels while maintaining the same computational and communication efficiency. Their proposed algorithm, UPGA-PL (Unbiased Pseudo-Gradient Aggregation with Packet Losses), employs a pseudo-gradient step rather than model averaging, and adjusts the aggregation weights for heterogeneous packet losses. In experimental evaluation, UPGA-PL outperforms existing methods in lossy environments and matches Federated Learning algorithms in lossless scenarios within a limited number of communication rounds.

Most work on federated learning assumes that clients operate on static datasets collected before training starts. This approach may be inefficient because 1) it ignores new samples clients collect during training, and 2) it may require a potentially long preparatory phase for clients to collect enough data. Moreover, learning on static datasets may be simply impossible in scenarios with small aggregate storage across devices. It is, therefore, necessary to design federated algorithms able to learn from data streams. In 34 O. Marfoq and G. Neglia, together with L. Kameni and R. Vidal from (Accenture Labs, France) formulate and study the problem of federated learning for data streams. They propose a general FL algorithm to learn from data streams through an opportune weighted empirical risk minimization. Their theoretical analysis provides insights to configure such an algorithm, and they evaluate its performance on a wide range of machine learning tasks.

7.3.6 Privacy and Fairness

In 39, C. Kaplan in collaboration with A.S. de Oliveira (SAP Labs France), Khawla Mallat (SAP Labs France), and Tanmay Chakraborty (SAP Labs France, Eurecom) investigate the impact of differential privacy on fairness notions for tabular data. They empirically analyze how different fairness notions, belonging to distinct classes of statistical fairness criteria, are impacted when one selects a model architecture suitable for DP-SGD (differentially private stochastic gradient descent), optimized for utility. Using standard datasets from ML fairness literature, they show that by selecting the optimal model architecture for DP-SGD, the differences across groups concerning the relevant fairness metrics more often decrease or are negatively impacted, compared to the non-private baseline, for which the optimal model architecture has also been selected to maximize utility. These findings challenge the understanding that differential privacy will necessarily exacerbate unfairness in deep learning models trained on biased datasets.

7.3.7 Data Injection Attacks in Power Systems

Since 2020, S. Perlaza in collaboration with X. Ye, I. Esnaola, and R. Harrison (Univ. of Sheffield) have studied sparse stealth attack constructions that minimize the mutual information between the state variables and the observations. In 25, the attack construction is formulated as the design of a multivariate Gaussian distribution that aims to minimize the mutual information while limiting the Kullback-Leibler divergence between the distribution of the observations under attack and the distribution of the observations without attack. The sparsity constraint is incorporated as a support constraint of the attack distribution. Two heuristic greedy algorithms for the attack construction are proposed. The first algorithm assumes that the attack vector consists of independent entries, and therefore, requires no communication between different attacked locations. The second algorithm considers correlation between the attack vector entries and achieves a better disruption to stealth tradeoff at the cost of requiring communication between different locations. Numerical evaluations show that it is feasible to construct stealth attacks that generate significant disruption with a low number of compromised sensors.

7.3.8 Graph Clustering

In 26 K. Avrachenkov and B.R. Vinay Kumar in collaboration with K. Alaluusua and L. Leskelä (Aalto University, Finland) consider the community recovery problem on a multilayer variant of the hypergraph stochastic block model (HSBM). Each layer is associated with an independent realization of a $d$-uniform HSBM on $N$ vertices. Given the similarity matrix containing the aggregated number of hyperedges incident to each pair of vertices, the goal is to obtain a partition of the $N$ vertices into disjoint communities. In this work, they investigate a semidefinite programming (SDP) approach and obtain information-theoretic conditions on the model parameters that guarantee exact recovery both in the assortative and the disassortative cases.

In 31, 60 K. Avrachenkov and L. Hauseux in collaboration with J. Zerubia (Ayana team) propose an original density estimator built from a cloud of points $X\in R^d$. To do this, they consider geometric graphs $G(X,r)$ on the cloud. These graphs depend on a radius $r$. By varying the radius, they see the emergence of large components around certain critical radii, which is the phenomenon of continuum percolation. Percolation allows us to have both a local view of the data (through local constraints on the radius $r$) and a global one (the emergence of macro-structures). With this tool, they address the problem of galaxy filament extraction. The density estimator gives us a relevant graph on galaxies. With an algorithm sharing the ideas of the Fréchet mean, they extract a subgraph from this graph, the galaxy filaments.

7.4.1 Optimal Rate Memory Tradeoff in Multi-Access Coded Caching

In 33 Vijith Kumar K. P. together with B. Kumar Rai and T. Jacob (IIT Guwahati, India) consider the $(N,K,L)$ multi-access caching network where $K$ users and $K$ caches are connected to a server with $N$ files, each of size $F$ bits, through a shared error-free broadcast channel. Each user has access to $L$ nearby caches, each of size $MF$ bits, in a cyclic wrap-around manner. Even after several previous attempts, the exact characterization of the optimal rate memory tradeoff is still an open problem except in the case where $L=K-1$ and $L=1$ with large cache $M\in [N/L·(K-1)/K,N/L]$. This paper determines the optimal rate memory tradeoff for the cache network with $L=K-2$ and $M\in [N/(K-2)·(K-1)/K,N/(K-2\left)\right]$. This is done by proposing a new caching scheme that operates at the memory rate pair $(N/(K-2)·(K-1)/K,1/K)$ and deriving a set of lower bounds to demonstrate the optimality of the scheme.

7.4.2 Deployment of Microservice-based Applications

In 18 F. Faticanti in collaboration with M. Savi (Univ. Milano-Bicocca, Italy), F. De Pellegrini (Univ. Avignon) and D. Siracusa (Fondazione Bruno Kessler, Italy) propose a new approach for the deployment of microservice-based applications in a Federated Fog Computing scenario under locality constraints for a subset of microservices of the application. The approach is based on a Breadth-First-Search (BFS) visit of the search space for the deployment of applications where the main objective is to minimize the deployment cost towards external fog domains with respect to the main provider. Experiments show that the proposed approach outperforms traditional deployment methods based on Depth-First-Search visits of the search space.

7.4.3 Learning Optimal Edge Processing with Offloading and Energy Harvesting

Modern portable devices can execute increasingly sophisticated AI models on sensed data. The complexity of such processing tasks is data-dependent and has relevant energy cost. In 30, A. Fox, F. De Pellegrini (Univ. Avignon) and E. Altman develop an Age of Information Markovian model for a system where multiple battery-operated devices perform data processing and energy harvesting in parallel. Part of their computational burden is offloaded to an edge server which polls devices at a given rate. The structural properties of the optimal policy for a single device-server system are derived. They permit to derive a new model-free reinforcement learning method specialized for monotone policies, namely Ordered Q-Learning, providing a fast procedure to learn the optimal policy. The method is oblivious to the devices’ battery capacities, the cost and the value of data batch processing and to the dynamics of the energy harvesting process. Finally, the polling strategy of the server is optimized by combining such policy improvement techniques with stochastic approximation methods. Extensive numerical results provide insight into the system properties and demonstrate that the proposed learning algorithms outperform existing baselines.

7.4.4 Pricing and resource allocation

We have been extending our research on games in networks where users compete over resources, to the case in which competition arises also between the users and the supplier of services and further to the case when the suppliers compete between each other through the prices of their services. This bundelling of services called Network slicing (NS) is a key technology in 5G that enables the customization and efficient sharing of network resources to support the diverse requirements of next-generation services.

In 15, M. Datar, E. Altman and H. Le Cadre (INOCS) consider a marketplace in the context of 5G network slicing, where Application Service Providers (ASP), i.e., slice tenants, providing heterogeneous services, are in competition for the access to the virtualized network resource owned by a Network Slice Provider (NSP), who relies on network slicing. They model the interactions between the end users (followers) and the ASPs (leaders) as a Stackelberg game. They prove that the competition between the ASPs results in a multi-resource Tullock rent-seeking game. To determine resource pricing and allocation, They devise two innovative market mechanisms.

In 16, S. Dhamal, W. Ben-Ameur, and T. Chahed (Télécom SudParis), E. Altman, A. Sunny (ITT Palakkad), and S. Poojary (Qualcomm India) study a distributed computing setting wherein a central entity seeks power from computational providers by offering a certain reward in return. The computational providers are classified into long-term stakeholders that invest a constant amount of power over time and players that can strategize on their computational investment. In this paper, they model and analyze a stochastic game where players arrive and depart over time. They prove that, in Markov perfect equilibrium, only players with cost parameters in a relatively low range which collectively satisfy a certain constraint in a given state, invest. They infer that players need not have knowledge about the system state and other players’ parameters, if the total power that is being received by the central entity is communicated to the players as part of the system’s protocol. If players are homogeneous and the system consists of a reasonably large number of players, They observe that the total power received by the central entity is proportional to the offered reward and does not vary significantly despite the players’ arrivals and departures, thus resulting in a robust and reliable system. They study by simulations and mean field approximation, how the players’ utilities are influenced by the system parameters.

In 51, M. Datar (currently at Orange Innovation), N. Modina (CNAM), R. El Azouzi (Univ. Avignon), and E. Altman propose an allocation scheme for network slicing based on the Fisher-market model and the Trading-post mechanism. The scheme aims to achieve efficient resource utilization while ensuring multi-level fairness, dynamic load conditions, and the protection of service level agreements (SLAs) for slice tenants. In the proposed scheme, each service provider (SP) is allocated a budget representing its infrastructure share or purchasing power in the market.

8.1.1 Accenture contract on the topic “Distributed Machine Learning for IoT applications” (Dec 2019 – November 2023)

Participants: Othmane Marfoq, Giovanni Neglia.

• Contractor: Accenture Labs
• Collaborators: Laetitia Kameni, Richard Vidal

IoT applications will become one of the main sources to train data-greedy machine learning models. Until now, IoT applications were mostly about collecting data from the physical world and sending them to the Cloud. Google’s federated learning already enables mobile phones, or other devices with limited computing capabilities, to collaboratively learn a machine learning model while keeping all training data locally, decoupling the ability to do machine learning from the need to store the data in the cloud. While Google envisions only users’ devices, it is possible that part of the computation is executed at other intermediate elements in the network. This new paradigm is sometimes referred to as Edge Computing or Fog Computing. Model training as well as serving (provide machine learning predictions) are going to be distributed between IoT devices, cloud services, and other intermediate computing elements like servers close to base stations as envisaged by the Multi-Access Edge Computing framework. The goal of this project is to propose distributed learning schemes for the IoT scenario, taking into account in particular its communication constraints. O. Marfoq is funded by this project. A first 12-month pre-PhD contract has been followed by a PhD grant.

8.1.2 Accenture “Plan de Relance” (PLR) contract on the topic “Energy-Aware Federated Learning” (Oct 2022 – September 2024)

Participants: Giovanni Neglia, Charlotte Rodriguez.

• Contractor: Accenture Labs
• Collaborators: Laura Degioanni, Laetitia Kameni, Richard Vidal

Deep neural networks have enabled impressive accuracy improvements across many machine learning tasks. Often the highest scores are obtained by the most computationally-hungry models. As a result, training a state-of-the-art model now requires substantial computational resources which demand considerable energy, along with the associated economic and environmental costs. Research and development of new models multiply these costs by thousands of times due to the need to try different model architectures and different hyper-parameters. In this project, we investigate a more algorithmic/system-level approach to reduce energy consumption for distributed ML training over the Internet. The postdoc of C. Rodriguez is funded by this project.

8.1.3 Cifre contract with NSP-SmartProfile “Automated and responsible recommendation systems for digital marketing” (August 2022 – July 2025)

Participants: Konstantin Avrachenkov, Ibtihal El Mimouni.

• Contractor: NSP-SmartProfile
• Collaborators: Hervé Baile, Julien Musso

SmartProfile is a marketing platform that allows to collect, to enhance and to analyze marketing data. Digital marketing campaigns continue to expand across all digital channels and media. The 'mass marketing' strategies implemented by most companies show limits in terms of performance and acceptance by clients, as well as in terms of their impact on the environment. In opposite to these practices, we believe that current technologies, particularly in terms of Artificial Intelligence (AI), should make marketing interactions more efficient and virtuous. Through this research project, we want to create an alternative solution to mass marketing by switching to an intelligent, automated and eco-responsible system, which will support the heterogeneity of data and the diversity of sectors, and whose purpose is to recommend the best content by determining the most relevant target and taking into account the communication constraints. This contract complements the Cifre thesis of Ibtihal El Mimouni.

8.1.4 Cifre contract with Orange Labs “Analytical modeling of large-scale wireless networks integrating RIS” (March 2023 – March 2026)

Participants: Eitan Altman, Julian Alfonso Santos Bustos.

• Contractor: Orange Labs
• Collaborators: Jean-Marc Kelif

A Reconfigurable Intelligent Surface (RIS) is a programmable surface structure that allows one to control the reflection of electromagnetic (EM) waves by changing the electric and magnetic properties of the surface. In the absence of RIS, short wavelentghs signals as in 5G, are subject to a huge attenuation when there is no direct line of sight channel. Within our collaboration we shall evaluate and optimize the position of RIS.

This contract complements the Cifre thesis of J. Santos.

8.1.5 Cifre contract with SAP “Privacy and fairness for ML” (December 2021 – December 2024)

Participants: Caelin Kaplan, Giovanni Neglia.

• Contractor: SAP Labs France
• Collaborators: Anderson Santana de Oliveira

There are increasing concerns among scholars and the public about bias, discrimination, and fairness in AI and machine learning. Decision support systems may present biases, leading to unfair treatment of some categories of individuals, for instance, systematically assigning high risk of recidivism in a criminal offense analysis system. Essentially, the analysis of whether an algorithm’s output is fair (e.g. does not disadvantages a group with respect to others) depends on substantial contextual information that often requires human intervention. There are though several metrics for fairness that have been developed, which may rely on collecting additional sensitive attributes (e.g., ethnicity) before imposing strong privacy guarantees to be used in any situation. It is known that differential privacy has the effect of hiding outliers from the data analysis, perhaps compounding existing bias in certain situations. This project encompasses the search for a mitigating strategy. This contract complements the Cifre thesis of C. Kaplan.

8.1.6 QITI 3IA Start-It-Up contract on the topic “Reinforcement Learning for Conversational Recommender Systems (RLCRS)” (April 2023 – March 2024)

Participants: Konstantin Avrachenkov, Hariprasad Manjunath Hegde.

• Contractor: QITI
• Collaborators: Christophe Bremard, Guillaume Dion

Qiti is a start-up created in Nice in 2021 which among other things develops a Conversational Recommender Systems (CRS) for insurance holders and insurers. The CRS should reduce the load on the workers of the insurers and to simplify the process of insurance establishment and modification. The goal of the present cooperation is to test and to improve various Reinforcement Learning schemes for CRS. The post-doc of H. Manjunath is funded by this contract.

9.1.1 Inria associate team not involved in an IIL or an international program

9.1.2 STIC/MATH/CLIMAT AmSud projects

9.2.1 Visits of international scientists

9.2.2 Visits to international teams

9.3.1 Horizon Europe

9.3.2 H2020 projects

NF-FOUNDS PC9 PEPR 5G

Participants: Eitan Altman, Samir M. Perlaza.

• Project Acronym:
  PEPR
• Project Title:
  Networks of the Future - Foundations of Future Communications Networks
• Program:
  ANR-22-PEFT-0010
• Coordinator:
  CEA (Dmitri Kténas), CNRS (Serge Verdeyme), IMT (Daniel Koffman)
• Duration:
  2023 - 2030
• Other Partners:
  EURECOM
• Abstract:
  The 5G network and the networks of the future represent a key issue for French and European industry, society and digital sovereignty. This is why the French government has decided to launch a dedicated national strategy. One of this strategy’s priority ambitions is to produce significant public research efforts so the national scientific community contributes fully to making progress that clearly responds to the challenges of 5G and the networks of the future. In this context, the CNRS, the CEA and the Institut Mines-Télécom (IMT) are co-leading the `5G’ acceleration PEPR to support upstream research into the development of advanced technologies for 5G and the networks of the future. Neo  is involved in the theme “Networks and Telecommunications” and more specifically in the `targeted projet 9 (PC9)” Foundations of Future Communications Networks (FOUNDS).

ANR PARFAIT

Participants: Eitan Altman, Ashok Krishnan Komalperlan Sindhu, Girik Maskara, Samir Medina Perlaza, Xinying Zou.

• Project Acronym:
  PARFAIT
• Project Title:
  Planning And leaRning For AI-Edge compuTing
• Coordinator:
  Avignon Univ.
• Duration:
  October 2021 – September 2025
• Other Partners:
  Conservatoire National des Arts et Métiers (CNAM), Univ. Savoie Mont Blanc (USMB)
• Abstract:
  The PARFAIT project develops theoretical foundations for distributed and scalable resource allocation schemes on edge computing infrastructures tailored for AI-based processing tasks. Algorithmic solutions will be developed based on the theory of constrained, delayed, and distributed Markov decision processes to account for edge service orchestration actions and quantify the effect of orchestration policies. Furthermore, using both game and team formulations, the project will pave the way for a theory of decentralized orchestration, a missing building block necessary to match the application quest for data proximity and the synchronization problems that arise when multiple edge orchestrators cooperate under local or partial system view. Finally, to achieve efficient online edge service orchestration, such solutions will be empowered with reinforcement learning techniques to define a suit of orchestration algorithms able to at once adapt over time to the applications’ load and cope with the uncertain information available from AI-based applications’ footprints.

BPI/PLR/PIA 5G Events Lab

Participants: Eitan Altman, Mandar Datar, Ashok Krishnan Komalan Sindhu, Vijith Kumar Kizhakke Purakkal, Giovanni Neglia, Samir M. Perlaza.

• Project Acronym:
  5G Events Labs
• Project Title:
  5G Events Labs
• Coordinator:
  Orange
• Duration:
  November 2020 – November 2023
• Other Partners:
  CEA Saclay, Ericsson.
• Abstract:
  The project aims to boost economic activity in the event, cultural and sports sectors, around major Olympic sites in France where Orange and its partners offer increased 5G coverage, technological platforms and appropriate support allowing companies to appropriate these technologies and incubate innovations in the field of services to spectators and organizers.

Inria Challenge FedMalin

Participants: Othmane Marfoq, Giovanni Neglia, Angelo Rodio.

• Project Acronym:
  FedMalin
• Project Title:
  FEDerated MAchine Learning over the INternet
• Coordinator:
  Giovanni Neglia and Aurélien Bellet (Inria team Magnet)
• Duration:
  November 2022 - November 2026
• Abstract:

  In many use-cases of Machine Learning (ML), data is naturally decentralized: medical data is collected and stored by different hospitals, crowdsensed data is generated by personal devices, etc. Federated Learning (FL) has recently emerged as a novel paradigm where a set of entities with local datasets collaboratively train ML models while keeping their data decentralized.

  FedMalin is a research project that spans 10 Inria research teams and aims to push FL research and concrete use-cases through a multidisciplinary consortium involving expertise in ML, distributed systems, privacy and security, networks, and medicine. We propose to address a number of challenges that arise when FL is deployed over the Internet, including privacy and fairness, energy consumption, personalization, and location/time dependencies. FedMalin will also contribute to the development of open-source tools for FL experimentation and real-world deployments, and use them for concrete applications in medicine and crowdsensing. The FedMalin Inria Challenge is supported by Groupe La Poste, sponsor of the Inria Foundation.

Exploratory action Inria MAMMALS

Participants: Francescomaria Faticanti, Giovanni Neglia.

• Project Acronym:
  MAMMALS
• Project Title:
  Memory-augmented Models for low-latency Machine-learning Serving
• Coordinator:
  Giovanni Neglia
• Duration:
  November 2020 - June 2023
• Other Partners:
  Univ. Turin, Polytechnic Turin, Univ. Verona, Univ. of Massachusetts, Northeastern Univ.
• Abstract:
  A machine learning model is often trained for inference’s purposes. Inference does not involve complex iterative algorithms and is therefore generally presumed to be easy. Nevertheless, it presents fundamental challenges that are likely to become dominant as machine learning adoption increases and machine learning systems are ubiquitously deployed and need to make timely and safe decisions in unpredictable environments. MAMMALS aims to provide low-latency inferences by running—close to the end user—simple machine learning models that can also take advantage of a (small) local data store of examples. The focus is on algorithms to learn online what to store locally to improve inference quality and achieve domain adaptation.

Exploratory action Inria IDEM

Participants: Emmanouil Athanasakos, Alain Jean-Marie, Samir M. Perlaza, Ke Sun.

• Project Acronym:
  IDEM
• Project Title:
  Information and Decision Making
• Coordinators:
  Samir M. Perlaza, Alain Jean-Marie
• Duration:
  November 2021 - November 2023
• Other Partners:
  Univ. of Sheffield, the National Chiao Tung Univ. in Taiwan, Princeton Univ.
• Abstract:
  IDEM aims to characterize the interplay between data acquisition and information processing in decentralized decision making by bringing together tools from information theory and game theory. This characterization is central in the comprehension of problems including decentralized optimization and Machine Learning subject to local information constraints.

10.1.1 Scientific events: organisation

10.1.2 Scientific events: selection

10.1.3 Journal

10.1.4 Invited talks

• K. Avrachenkov delivered a
  • plenary talk “Graph Clustering Problem: Beyond Binary Interactions” at the 59th ANZIAM Conference, Cairns, Australia, held on 5-9 February 2023;
  • Specialist Lecture “Singularly Perturbed Markovian Models: From Queues to Web Ranking and Reinforcement Learning“ on Monday 13 February, at University of South Australia;
  • Specialist Lecture “Random-walk Based Sampling in Social Networks“ on Wednesday 15 February, at RMIT;
  • Specialist Lecture “Random Graph Models, Network Centralities and Graph Clustering“ on Friday 17 February, at Australian Bureau of Satistics;
  • Specialist Lecture “Reinforcement Learning for Restless Bandits" on Monday 20 February, at University of Newcastle;
  • Public Lecture “Aesthetics and ubiquitous applications of Markov chains“ on Wednesday 22 February, at The University of Queensland;
  • an invited presentation "Reinforcement Learning Methods for Weakly Coupled MDPs" at the Workshop on restless bandits, index policies and applications in reinforcement learning, Grenoble, on 21 November.
• J. Clarkson delivered an invited talk "On the Price of Information in Queueing" at 21st INFORMS Applied Probability Society Conference, Nancy, on June 28-30.
• C. Kaplan delivered the following invited talks:
  • “A Cautionary Tale: On the Role of Reference Data in Empirical Privacy Defenses” at SAP's Machine Learning Conference, March 22 - March 23, Remote.
  • “Membership Inference Attacks in Machine Learning” for SAP's explAIn Series, December 7, Remote.
• V. Kumar B.R. delivered the following invited talks
  • "Community detection on block models with geometric kernels" at 21st INFORMS Applied Probability Society Conference, Nancy, on June 28-30.
  • "Community detection on Block Models with Geometric Kernels", in the CNI Networks Seminar Series at IISc, Bangalore, on December 5.
• G. Neglia delivered the following invited talks:
  • “Personalized Federated Learning” at Stellantis'Data Science Community meetup, online, 22/9/2023.
  • “Personalized Federated Learning” at IEEE Systems, Man, and Cybernetics (SMC) Society Italy Chapter, 5/5/2023.
• S. Perlaza delivered the following invited talks:
  • “On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation” at the Ecole Normale Supérieure (ENS) de Lyon. Laboratoire de l'Informatique du Parallélisme (LIPS). Lyon, France, June 21, 2023. Host: Prof. Francesco Bronzino.
  • “An Upper Bound on the Error Induced by Saddlepoint Approximations—Applications to Wireless Communications” at the Workshop on “Performance Guarantees in Wireless Networks”. Laboratory for Information, Networking and Communication Sciences (LINCS). Palaiseau, France, March 8, 2023. Host: Prof. Francois Baccelli and Prof. Jean-Marie Gorce.
  • “Pricing Models for Digital Renting Platforms” at Booking.com, Amsterdam, Netherlands, October 18, 2023. Host: Dr. Christina Katsimerou.
• C. Rodriguez delivered a talk on "How can we evaluate the energy consumption of Machine Learning?" at Journées de Recherche en Apprentissage Frugal, Grenoble, 13-14 December, 2023.

10.1.5 Invited papers

S. Alouf was invited to write a technical perspective on a paper appearing in the Research Highlights section of the Communications of the ACM 59.

10.1.6 Leadership within the scientific community

• S. Alouf
  • is an elected member at the Board of Directors of ACM SIGMETRICS (July 2019 - June 2023);
  • is a member of the Equality and Diversity committee of ACM SIGMETRICS (November 2019 - June 2023);
  • is a member of the Conference Advisory committee of ACM SIGMETRICS (November 2019 - June 2023).
• E. Altman
  • is Fellow Member of IEEE;
  • is Member of WG 7.3 of IFIP on Computer System Modeling;
  • is Member of WG 6.3 of IFIP on Performance of Communications Systems.
• K. Avrachenkov
  • was the 2023 AMSI-ANZIAM Lecturer;
  • is a member of Conseil Scientifique & Pédagogique EUR DS4H Univ. Côte d'Azur.
• S. Perlaza
  • is a member of the Digital Presence Committee of the IEEE Information Theory Society.
  • is a workpackage leader of the PEPR - Réseaux du Futur – A project funded by the French National Agency for Research (ANR) via the project n°ANR-22-PEFT-0010 of the France 2030 program
  • is the organizer of the PC9 Seminar on Wireless Communications, a national online seminar part of the PEPR – Réseaux du Futur.

10.1.7 Research administration

• S. Alouf
  • was member of the competitive exam jury for a researcher position (CRCN/ISFP) at Inria Sophia Antipolis Méditerranée in 2023.
  • is a member of the Colloquium Jacques Morgenstern Committee at Inria Sophia Antipolis Méditerranée, since March 2023
  • is a member of NICE, the Invited Researchers Committee of Inria Sophia Antipolis Méditerranée, since June 2020;
  • is member of CLF, the training committee of Inria Sophia Antipolis Méditerranée, since November 2014;
  • is vice-head of project-team Neo since January 2017.
• K. Avrachenkov was in charge of the Activity Report process for Inria Sophia Antipolis Méditerranée.
• A. Jean-Marie
  • is the scientific coordinator of Inria activities in Montpellier (since 2008); as part of this duty, he represents Inria at: the Scientific Council of the Doctoral School “Sciences and Agrosciences” of the Univ. of Avignon; at the Regional Conference of Research Organisms (CODOR); at the board of the Labex NUMEV.
  • is Head of project-team NEO since January 2017
• P. Nain chaired the Inria ad-hoc commission in charge of evaluating applications for the double 2023-2024 bonus campaign (RIPEC-C3). [He also chaired this commission for the 2022 campaign.]
• G. Neglia is
  • an elected member of Inria evaluation committee, since September 2023;
  • a member of the steering commitee of UniCA Graduate School of Digital Systems for Humans (DS4H) since September 2022.
• S. Perlaza
  • is a representant (suppléant, collège A) before the Comité de Centre Inria d'Université Côte d'Azur
  • is a Member of the Bureau de l'Académie Réseaux, Information et Société Numérique, Académie d'Excellence d'Univ Côte d'Azur.
  • is a Member of the Département Disciplinaire Informatique de l'Univ Côte d'Azur.

10.2.1 Teaching

10.2.2 Supervision

10.2.3 Juries

International journals

• 13 articleK.Konstantin Avrachenkov, E.Evsey Morozov and R.Ruslana Nekrasova. Stability analysis of two-class retrial systems with constant retrial rates and general service times.Performance Evaluation159January 2023, 102330HALDOIback to text
• 14 articleV.Víctor Bucarey López, E.Eugenio Della Vecchia, A.Alain Jean-Marie and F.Fernando Ordoñez. Stationary Strong Stackelberg Equilibrium in Discounted Stochastic Games.IEEE Transactions on Automatic Control6892023, 5271 - 5286HALDOI
• 15 articleM.Mandar Datar, E.Eitan Altman and H.Hélène Le Cadre. Strategic Resource Pricing and Allocation in a 5G Network Slicing Stackelberg Game.IEEE Transactions on Network and Service Management2012023, 1932--4537HALDOIback to text
• 16 articleS.Swapnil Dhamal, W.Walid Ben-Ameur, T.Tijani Chahed, E.Eitan Altman, A.Albert Sunny and S.Sudheer Poojary. A game theoretic framework for distributed computing with dynamic set of agents.Annals of Operations ResearchFebruary 2023HALDOIback to text
• 17 articleR.Ranbir Dhounchak, V.Veeraruna Kavitha and E.Eitan Altman. Viral Marketing Branching Processes.Computer Communications198January 2023, 140-156HALDOIback to text
• 18 articleF.Francescomaria Faticanti, M.Marco Savi, F.Francesco De Pellegrini and D.Domenico Siracusa. Locality-aware deployment of application microservices for multi-domain fog computing.Computer Communications203April 2023, 180-191HALDOIback to text
• 19 articleA.Alain Jean-Marie and M.Mabel Tidball. Dynamic fishing with endogenous habitat damage.Dynamic Games and ApplicationsJuly 2023HALDOIback to text
• 20 articleS. M.Samir M Perlaza, G.Gaetan Bisson, I.Iñaki Esnaola, A.Alain Jean-Marie and S.Stefano Rini. Empirical Risk Minimization with Relative Entropy Regularization.IEEE Transactions on Information Theory2024HALDOIback to textback to text
• 21 articleA.Angelo Rodio, F.Francescomaria Faticanti, O.Othmane Marfoq, G.Giovanni Neglia and E.Emilio Leonardi. Federated Learning Under Heterogeneous and Correlated Client Availability.IEEE/ACM Transactions on Networking2023, 1-10HALDOIback to text
• 22 articleT. S.Tareq Si Salem, G.Gabriele Castellano, G.Giovanni Neglia, F.Fabio Pianese and A.Andrea Araldo. Toward inference delivery networks: distributing machine learning with optimality guarantees.IEEE/ACM Transactions on NetworkingAugust 2023, 1HALDOI
• 23 articleT.Tareq Si Salem, G.Giovanni Neglia and S.Stratis Ioannidis. No-regret Caching via Online Mirror Descent.ACM Transactions on Modeling and Performance Evaluation of Computing Systems84August 2023, 1-32HALDOI
• 24 articleG.Gayane Vardoyan, P.Philippe Nain, S.Saikat Guha and D.Don Towsley. On the Capacity Region of Bipartite and Tripartite Entanglement Switching.ACM Transactions on Modeling and Performance Evaluation of Computing Systems81-2June 2023, 1-18HALDOI
• 25 articleX.Xiuzhen Ye, I.Iñaki Esnaola, S. M.Samir M. Perlaza and R. F.Robert F Harrison. Stealth Data Injection Attacks with Sparsity Constraints.IEEE Transactions on Smart Grid144July 2023, 3201 -- 3209HALDOIback to text

International peer-reviewed conferences

• 26 inproceedingsK.Kalle Alaluusua, K.Konstantin Avrachenkov, B. R.B R Vinay Kumar and L.Lasse Leskelä. Multilayer Hypergraph Clustering Using the Aggregate Similarity Matrix.Lecture Notes in Computer ScienceWAW 2023 - Algorithms and Models for the Web GraphLNCS-13894Algorithms and Models for the Web Graph 18th International Workshop, WAW 2023, Toronto, ON, Canada, May 23–26, 2023, ProceedingsToronto, CanadaSpringer Nature SwitzerlandMarch 2023, 83-98HALDOIback to text
• 27 inproceedingsY.Younes Ben Mazziane, F.Francescomaria Faticanti, G.Giovanni Neglia and S.Sara Alouf. No-Regret Caching with Noisy Request Estimates.IEEE VCC 2023 - IEEE Virtual Conference on CommunicationsNew York (ONLINE), United StatesNovember 2023HALback to text
• 28 inproceedingsF.Francisco Daunas, I.Iñaki Esnaola, S. M.Samir M Perlaza and H. V.H. Vincent Poor. Analysis of the Relative Entropy Asymmetry in the Regularization of Empirical Risk Minimization.Proceedings of the IEEE International Symposium on Information Theory (ISIT)(ISIT 2023 - IEEE International Symposium on Information TheoryTaipei, TaiwanJune 2023HALDOIback to textback to text
• 29 inproceedingsF.Francescomaria Faticanti and G.Giovanni Neglia. Optimistic Online Caching for Batched Requests.IEEE XploreICC 2023 - IEEE International Conference on CommunicationsICC 2023 - IEEE International Conference on CommunicationsRome, FranceIEEEMay 2023, 6243-6248HALDOIback to text
• 30 inproceedingsA.Andrea Fox, F.Francesco De Pellegrini and E.Eitan Altman. Learning Optimal Edge Processing with Offloading and Energy Harvesting.MSWiM '23: Int'l ACM Conference on Modeling Analysis and Simulation of Wireless and Mobile SystemsMontreal Quebec Canada, CanadaACMOctober 2023, 83-92HALDOIback to text
• 31 inproceedingsL.Louis Hauseux, K.Konstantin Avrachenkov and J.Josiane Zerubia. Graph Based Approach for Galaxy Filament Extraction.Studies in Computational IntelligenceComplex Networks 2023 - The 12th International Conference on Complex Networks and their ApplicationsStudies in Computational IntelligenceMenton, FranceNovember 2023HALDOIback to text
• 32 inproceedingsA.Ashok Krishnan K. S., S. M.Samir M. Perlaza and E.Eitan Altman. Pricing Models for Digital Renting Platforms.ASMTA 2023 - International Conference on Analytical & Stochastic Modelling Techniques & ApplicationsFlorence, FranceJune 2023HALDOIback to text
• 33 inproceedingsV.Vijith Kumar K. P., B.Brijesh Kumar Rai and T.Tony Jacob. The Optimal Rate Memory Tradeoff in Multi-Access Coded Caching: Large Cache Size.IEEE XploreITW 2023 - IEEE Information Theory WorkshopIEEE (first ITW conference of the year) Information Theory Workshop (ITW)Saint-Malo, FranceIEEEApril 2023, 165-169HALDOIback to text
• 34 inproceedingsO.Othmane Marfoq, G.Giovanni Neglia, L.Laetitia Kameni and R.Richard Vidal. Federated Learning for Data Streams.Proceedings of The 26th International Conference on Artificial Intelligence and StatisticsAISTATS 2023 - The 26th International Conference on Artificial Intelligence and StatisticsValencia (Espagne), SpainApril 2023HALback to text
• 35 inproceedingsT.Tejas Pagare, V. S.Vivek S Borkar and K.Konstantin Avrachenkov. Full Gradient Deep Reinforcement Learning for Average-Reward Criterion.Proceedings of Machine Learning Research (PMLR)L4DC - The 5th Annual Learning for Dynamics and Control Conference211Learning for Dynamics and Control Conference, 15-16 June 2023, Philadelphia, PAPhiladelphia, United StatesJune 2023, 235-247HALback to text
• 36 inproceedingsS. M.Samir M. Perlaza, I.Iñaki Esnaola, G.Gaetan Bisson and H. V.H Vincent Poor. On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation.ISIT 2023 - IEEE International Symposium on Information TheoryTaipei, TaiwanJune 2023HALDOIback to text
• 37 inproceedingsA.Angelo Rodio, F.Francescomaria Faticanti, O.Othmane Marfoq, G.Giovanni Neglia and E.Emilio Leonardi. Federated Learning under Heterogeneous and Correlated Client Availability.IEEE INFOCOM 2023 - IEEE Conference on Computer CommunicationsIEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications SocietiesNew York City, United StatesIEEEMay 2023, 1-10HALDOIback to textback to textback to text
• 38 inproceedingsA.Angelo Rodio, G.Giovanni Neglia, F.Fabio Busacca, S.Stefano Mangione, S.Sergio Palazzo, F.Francesco Restuccia and I.Ilenia Tinnirello. Federated Learning with Packet Losses.IEEE XploreWPMC 2023 - 26th International Symposium on Wireless Personal Multimedia Communications2022 25th International Symposium on Wireless Personal Multimedia Communications (WPMC)Tampa, United StatesIEEENovember 2023, 1-6HALDOIback to text
• 39 inproceedingsA.Anderson Santana de Oliveira, C.Caelin Kaplan, K.Khawla Mallat and T.Tanmay Chakraborty. An Empirical Analysis of Fairness Notions under Differential Privacy *.PPAI 2023 - Fourth AAAI Workshop on Privacy-Preserving Artificial IntelligenceWashington D.C., United StatesFebruary 2023HALback to text
• 40 inproceedingsT.Tareq Si Salem, G.Georgios Iosifidis and G.Giovanni Neglia. Enabling Long-term Fairness in Dynamic Resource Allocation.ACM digital library2023 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer SystemsSIGMETRICS '23: ACM SIGMETRICS International Conference on Measurement and Modeling of Computer SystemsOrlando (FL), United StatesJune 2023HALDOIback to text
• 41 inproceedingsK.Ke Sun, S. M.Samir M. Perlaza and A.Alain Jean-Marie. 2×2 Zero-Sum Games with Commitments and Noisy Observations.ISIT 2023 - IEEE International Symposium on Information TheoryTaipei, TaiwanJune 2023HALDOIback to text
• 42 inproceedingsR.Raphaël Taisant, M.Mandar Datar, H.Hélène Le Cadre and E.Eitan Altman. Learning Market Equilibria Using Performative Prediction: Balancing Efficiency and Privacy.ECC 2023 - European Control Conference2023 European Control Conference (ECC)Bucharest, RomaniaJune 2023HALDOIback to textback to text
• 43 inproceedingsB. R.B R Vinay Kumar. Spatial Queues with Nearest Neighbour Shifts.ITC-35 - 35th International Teletraffic Congress : Networked Systems and ServicesTorino, ItalyOctober 2023HALback to text

Edition (books, proceedings, special issue of a journal)

• 44 periodicalACM SIGMETRICS 2023 Student Research Competition.ACM SIGMETRICS Performance Evaluation Review513December 2023, 2HALDOIback to text
• 45 periodicalSpecial Issue : Multi-Agent Dynamic Decision Making and Learning.Dynamic Games and Applications13January 2023HALDOIback to textback to text
• 46 periodicalPOMACS V7, N1, March 2023 : Editorial.Proceedings of the ACM on Measurement and Analysis of Computing Systems 71March 2023, 1-1HALDOIback to text
• 47 periodicalPOMACS V7, N2, June 2023 Editorial.Proceedings of the ACM on Measurement and Analysis of Computing Systems 7Proceedings of the ACM on Measurement and Analysis of Computing Systems2May 2023, 1-2HALDOIback to text

Doctoral dissertations and habilitation theses

• 48 thesisO.Othmane Marfoq. Tackling heterogeneity in federated learning systems.Université Côte d'AzurDecember 2023HALback to text

Reports & preprints

• 49 miscE. M.Emmanouil M Athanasakos and S. M.Samir M Perlaza. Leveraging Noisy Observations in Zero-Sum Games.January 2024HAL
• 50 miscF.Francisco Cabo, M.Mabel Tidball and A.Alain Jean-Marie. Positional and conformist effects in public good provision. Strategic interaction and inertia.June 2023, 33 p.HAL
• 51 miscM.Mandar Datar, N.Naresh Modina, R.Rachid El Azouzi and E.Eitan Altman. Fisher Market Model based Resource Allocation for 5G Network Slicing.2023HALback to text
• 52 reportF.Francisco Daunas, I.Iñaki Esnaola, S. M.Samir M. Perlaza and H. V.H. Vincent Poor. Empirical Risk Minimization with Relative Entropy Regularization Type-II.RR-9508INRIA, Centre Inria d'Université Côte d'Azur, Sophia AntipolisMay 2023HALback to text
• 53 reportF.Francisco Daunas, I.Iñaki Esnaola, S. M.Samir M. Perlaza and H. V.H. Vincent Poor. Empirical Risk Minimization with f-Divergence Regularization in Statistical Learning.RR-9521InriaOctober 2023HALback to text
• 54 reportA.Ashok Krishnan K. S., S. M.Samir M. Perlaza and E.Eitan Altman. Pricing for Platforms: Games, Equilibria and Cooperation.RR-9510InriaJune 2023HALback to text
• 55 miscH.Hélène Le Cadre, M.Mandar Datar, M.Mathis Guckert and E.Eitan Altman. Learning Market Equilibria Preserving Statistical Privacy Using Performative Prediction.June 2023HALback to text
• 56 reportK.Ke Sun, S. M.Samir M. Perlaza and A.Alain Jean-Marie. 2 × 2 Zero-Sum Games with Commitments and Noisy Observations.RR-9505Inria - Sophia AntipolisMay 2023HALback to text
• 57 miscB. R.B R Vinay Kumar. Spatial Queues with Nearest Neighbour Shifts.September 2023HALback to text
• 58 reportX.Xinying Zou, S. M.Samir M. Perlaza, I.Iñaki Esnaola and E.Eitan Altman. The Worst-Case Data-Generating Probability Measure.RR-9515INRIAAugust 2023HALback to text

Other scientific publications

• 59 articleS.Sara Alouf. Technical Perspective: Can We Uncover Private Backbone Infrastructures?Communications of the ACM668August 2023, 94HALDOIback to text
• 60 inproceedingsL.Louis Hauseux, K.Konstantin Avrachenkov and J.Josiane Zerubia. Un nouvel estimateur des niveaux de densité utilisant les graphes et complexes simpliciaux.Application à la détection des clusters de galaxies..XVIe Journées de géostatistiques (Fontainebleau, 7-8 septembre 2023) organisé par les Mines de Paris - PSLFontainebleau, FranceSeptember 2023HALback to text