6.1.1 marmoteCore

• Name:
  Markov Modeling Tools and Environments - the Core
• Keywords:
  Modeling, Stochastic models, Markov model
• Functional Description:

  marmoteCore is a C++ environment 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.

  This software was started within the ANR MARMOTE project: ANR-12-MONU-00019.

• News of the Year:
  No active development. Current development lies now in the MARTO project (next generations of PSI and marmoteCore) and in the forthcoming Marmote project.
• URL:
  https://­gitlab.­inria.­fr/­PSI/­marmotecore/
• Publications:
  hal-01651940, hal-01276456
• Contact:
  Alain Jean-Marie
• Participants:
  Alain Jean-Marie, Hlib Mykhailenko, Benjamin Briot, Franck Quessette, Issam Rabhi, Jean-Marc Vincent, Jean-Michel Fourneau
• Partners:
  Université de Versailles St-Quentin-en-Yvelines, Université Paris Nanterre

7.1.1 Count-Min Sketch with Conservative Updates

Count-Min Sketch with Conservative Updates (CMS-CU) is a popular algorithm to approximately count items’ appearances in a data stream. Despite CMS-CU’s widespread adoption, the theoretical analysis of its performance is still wanting because of its inherent difficulty. In 31, 19 Y. Ben Mazziane, S. Alouf, and G. Neglia propose a novel approach to study CMS-CU and derive new upper bounds on the expected value and the CCDF of the count estimation error under an i.i.d. request process. The formulas obtained can be successfully employed to derive improved estimates for the precision of heavy-hitter detection methods and improved configuration rules for CMS-CU. The bounds have been evaluated both on synthetic and real traces.

7.1.2 Infinite Dimensional Linear Programming Approach to Optimal Stochastic Control

In 16, K. Avrachenkov together with V. Gaitsgory and L. Gamertsfelder (both from Macquarie Univ., Australia) study asymptotic properties of problems of control of stochastic discrete time systems with time averaging and time discounting optimality criteria and with general compact state and action spaces (equivalently Markov Decision Processes, MDPs), and they establish that the Cesàro and Abel limits of the optimal values in such problems can be estimated with the help of a certain infinite-dimensional (ID) linear programming (LP) problem and its dual.

7.1.3 Online Algorithms for Estimating Change Rates of Web Pages

In 17, K. Avrachenkov and K. Patil (former Neo member) with G. Thoppe (Indian Institute of Science, IISc, Bangalore, India) consider the following optimization problem: maximize the freshness of the local cache of a web crawler subject to the crawling frequencies being within prescribed bounds. While tractable algorithms do exist to solve this problem, these either assume the knowledge of exact page change rates or use inefficient methods such as MLE for estimating the same. The authors provide three novel schemes for online estimation of page change rates, all of which have extremely low running times per iteration. The first is based on the law of large numbers and the second on stochastic approximation. The third is an extension of the second and includes a heavy-ball momentum term. All these schemes only need partial information about the page change process, i.e., they only need to know if the page has changed or not since the last crawled instance. Numerical experiments (based on real and synthetic data) are also provided that demonstrate the superiority of the proposed estimators over existing ones such as MLE. The algorithms are also readily applicable to the synchronization of databases and network inventory management.

7.1.4 Red Light Green Light Method for Solving Large Markov Chains

Discrete-time discrete-state finite Markov chains are versatile mathematical models for a wide range of real-life stochastic processes. One of most common tasks in studies of Markov chains is computation of the stationary distribution. In 15, K. Avrachenkov and P. Brown, in collaboration with N. Litvak (Twente University, the Netherlands) propose a new controlled, easily distributed algorithm for this task, briefly summarized as follows: at the beginning, each node receives a fixed amount of cash (positive or negative), and at each iteration, some nodes receive 'green light' to distribute their wealth or debt proportionally to the transition probabilities of the Markov chain; the stationary probability of a node is computed as a ratio of the cash distributed by this node to the total cash distributed by all nodes together. The proposed method includes as special cases a wide range of known, very different, and previously disconnected methods including power iterations, Gauss-Southwell, and online distributed algorithms. The authors prove exponential convergence of our method, demonstrate its high efficiency, and derive scheduling strategies for the green-light, that achieve convergence rate faster than state-of-the-art algorithms.

7.1.5 Stability and Partial Instability of Multi-Class Retrial Queues

In most standard queueing systems, in the case of overload, customers are either lost or experience very long or infinite delays. However, in many real systems, rejected or significantly delayed customers leave the queue and then return later. This natural phenomenon motivates the development of retrial queues. In retrial queueing models, once a customer is rejected, he or she goes into the orbit and retries from there. This significantly increases the complexity of the system and makes the analysis of retrial queues challenging. There are two main types of retrial: independent retrials and constant rate retrials. In the former case the retrying customers are in “competition” and retry from the orbit independently. In the latter case, retrying customers wait in the orbit, according to the FIFO principle, and retry only when they are at the front of the orbit queue. In 18, K. Avrachenkov overviews the stability conditions for multi-class retrial queues with constant retrial rates. Also, a very interesting phenomenon of partial (or local) stability is discussed when some orbit sizes are stable (tight) whereas the other orbit sizes grow to infinity. This type of queueing models can find application in access control systems, and in particular, in access control system in overload.

7.1.6 Random walks for Gene Prioritization

Prioritizing genes for their role in drug sensitivity, is an important step in understanding drugs mechanisms of action and discovering new molecular targets for co-treatment. In 29, A. Jean-Marie, together with F. Cazals and D. Mazauric (Inria Abs team), J. Roux, A. Sales de Quieroz and G. Sales Santa Cruz (all from Univ. Côte d'Azur), introduce Genetrank, a method to prioritize the genes in some source set for their likelihood to regulate the genes in some target set. Genetrank uses asymmetric random walks with restarts, absorbing states, and a suitable renormalization scheme. Neo's software Marmote, successor of marmoteCore (Section 6.1.1) was used for the intensive numerical experiments.

7.1.7 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 62, 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.

7.3.1 Online Learning

In 30, T. Si Salem and G. Neglia in collaboration with G. Iosifidis (TU Delft, Netherlands) study the fairness of dynamic resource allocation problem under the $\alpha$-fairness criterion. They recognize two different fairness objectives that naturally arise in this problem: the well-understood slot-fairness objective that aims to ensure fairness at every timeslot, and the less explored horizon-fairness objective that aims to ensure fairness across utilities accumulated over a time horizon. They argue that horizon-fairness comes at a lower price in terms of social welfare. They study horizon-fairness with regret as a performance metric and prove that vanishing regret cannot be achieved in presence of an unrestricted adversary. They propose restrictions on the adversary’s capabilities corresponding to realistic scenarios and an online policy that indeed guarantees vanishing regret under these restrictions. They demonstrate the applicability of the proposed fairness framework to a representative resource management problem considering a virtualized caching system where different caches cooperate to serve content requests.

7.3.2 Reinforcement Learning for Restless Bandits

In 14, K. Avrachenkov and V.S. Borkar (Indian Institute of Technology Bombay, IITB, India) present a novel reinforcement learning algorithm for multi-armed restless bandits with average reward, using the paradigms of Q-learning and Whittle index. Specifically, the authors leverage the structure of the Whittle index policy to reduce the search space of Q-learning, resulting in major computational gains. Rigorous convergence analysis is provided, supported by numerical experiments. The numerical experiments show excellent empirical performance of the proposed scheme.

Then, in 48, 64, K. Avrachenkov in collaboration with V.S. Borkar (Indian Institute of Technology Bombay, IITB, India), U. Ayesta (IRIT, CNRS) and F. Robledo (Univ. Basque Country, Spain) study reinforcement learning for restless bandits with discounted reward. Specifically, they present QWI and QWINN, two algorithms capable of learning the Whittle indices for the total discounted criterion. The key feature is the usage of two timescales, a faster one to update the state-action Q-values, and a relatively slower one to update the Whittle indices. In our main theoretical result the authors show that QWI, which is a tabular implementation, converges to the real Whittle indices. QWINN, an adaptation of QWI algorithm using neural networks to compute the Q-values on the faster timescale, is able to extrapolate information from one state to another and scales naturally to large state-space environments. Numerical computations show that QWI and QWINN converge much faster than the standard Q-learning algorithm, neural-network based approximate Q-learning and other state of the art algorithms.

7.3.3 Federated Learning

The increasing size of data generated by smartphones and IoT devices motivated the development of Federated Learning (FL), a framework for on-device collaborative training of machine learning models. Federated learning allows clients to collaboratively learn statistical models while keeping their data local.

7.3.4 Distributed Inference

Small IoT devices, such as drones and lightweight battery-powered robots, are emerging as a major platform for the deployment of AI/ML capabilities. Autonomous and semiautonomous device operation relies on the systematic use of deep neural network models for solving complex tasks, such as image classification. The challenging restrictions of these devices in terms of computing capabilities, network connectivity, and power consumption are the main limits to the accuracy of latencysensitive inferences. In 34, G. Castellano and G. Neglia, together with F. Pianese and T. Zhang (Nokia Bell Labs) and D. Carra (Univ. of Verona, Italy) present ReBEL, a split computing architecture enabling the dynamic remote offload of partial computations or, in alternative, a local approximate labeling based on a jointly-trained classifier. Their approach combines elements of head network distillation, early exit classification, and bottleneck injection with the goal of reducing the average end-to-end latency of AI/ML inference on constrained IoT devices.

7.3.5 Empirical Risk Minimization with Relative Entropy Regularization

In the context of the exploratory action IDEM (Information and Decision Making), in 40, 55, 56 and 57, S. M. Perlaza and A. Jean-Marie, together with G. Bisson (Univ. de la Polynésie française), I. Esnaola (Univ. of Sheffield), and S. Rini (National Chiao Tung Univ.), studied the problem of empirical risk minimization (ERM) with relative entropy regularization (ERM-RER) in the context of supervised learning from the perspective of measure theory. In particular, the relative entropy is assumed to be with respect to a given measure, the reference measure, and not necessarily a probability mesure. This provides a unified treatment of two relevant problems in supervised learning. First, when the reference measure is a probability measure, the ERM-RER problem is shown to be a risk-information minimization problem. Alternatively, when the reference measure is the Lebesgue measure or a counting measure, the solution of the ERM-RER problem is shown to be identical to the solution to an entropy minimization problem with linear constraints, as the one typically induced by Jayne’s maximum entropy principle. The main result consists in a number of properties for the solution to the ERM-RER in terms of the reference measure, the regularization factor, and the training data. Some of the most important properties are described hereunder:

(i) The optimal solution to the ERM-RER is a probability measure that is unique and concentrates into a set arbitrarily small containing the minimizers of the empirical risk with arbitrarily high probability. The tradeoff between the cardinality of such set and the probability is governed by the regularization factor.

(ii) The expected value of the empirical risk, with respect to the ERM-RER optimal measure, is decreasing with the regularization factor. Nonetheless, via simple examples, monotonicity of the variance and higher cumulants is shown to be subject to conditions.

(iii) The transport of the ERM-RER optimal measure through the loss function is a sub-Gaussian probability measure. This property is central to study the sensitivity of the empirical risk for a particular data set with respect to changes around the optimal ERM-RER optimal measure.

7.4.1 Dynamic Social Learning under Graph Constraints

In 13, K. Avrachenkov together with V.S. Borkar, S. Moharir and S. M. Shah (all from Indian Institute of Technology Bombay, India) introduce a model of graph-constrained dynamic social choice with reinforcement modeled by positively $\alpha$-homogeneous rewards. They show that its empirical process, which can be written as a stochastic approximation recursion with Markov noise, has the same probability law as a certain vertex reinforced random walk. Furthermore, its fluid limit has a relation to the replicator dynamics. They use these equivalences to show that for $\alpha >0$, the asymptotic outcome concentrates around the optimum in a certain limiting sense when 'annealed' by letting $\alpha \to \infty$ slowly.

7.4.2 Stochastic Game with a dynamic set of players

In 22, S. Dhamal (Chalmers Univ. of Technology, Sweden) in collaboration with W. Ben-Ameur and T. Chahed (both from Telecom SudParis, France), E. Altman, A. Sunny (from IIT Palakkad, India) and S. Poojary (Qualcomm India), study a stochastic game with a dynamic set of players, for modeling and analyzing their computational investment strategies in distributed computing. Players obtain a certain reward for solving a problem, while incurring a certain cost based on the invested time and computational power. The authors relate the model to blockchain mining, and show that the framework is applicable to certain other distributed computing settings as well. The authors consider a particular yet natural scenario where the rate of solving the problem is proportional to the total computational power invested by the players. It is shown that, in Markov perfect equilibrium, players with cost parameters exceeding a certain threshold, do not invest; while those with cost parameters less than this threshold, invest maximal power. With extensive simulations and insights through mean field approximation, the authors study the effects of players' arrival/departure rates and the system parameters on the players' utilities.

7.4.3 Games with incomplete information

Asymmetry and/or incompleteness of information in the context of Game Theory typically leads to situations where one of the players can take an extra advantage over her opponent.

One such situation is analyzed in 58 by S.M. Perlaza, K. Sun and A. Jean-Marie. In this paper, two-player, two-action, zero-sum games are studied under the following assumptions: (1) One of the players (the leader) publicly and irrevocably commits to choose its actions by sampling a given probability measure (strategy); (2) The leader announces its action, which is observed by its opponent (the follower) through a binary channel; and (3) 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 and be often different from the Nash and Stackelberg equilibria. Even subject to noise, observing the actions of the leader is either beneficial or immaterial to the follower for all possible commitments: acquiring information indeed leads to an improved payoff. When the commitment is observed subject to a distortion, the equilibrium does not necessarily exist. Nonetheless, the leader might still obtain some benefit in some specific cases subject to equilibrium refinements. For instance, $ϵ$-equilibria might exist in which the leader commits to suboptimal strategies that allow unequivocally predicting the best response of its opponent.

As a preliminary to this analysis, K. Sun has systematically reviewed in 59 the properties of Nash equilibria in two-player, two-action, zero-sum games.

This research is part of the IDEM project (Section 9.4).

7.4.4 Positionalism and Conformism in Public Good Games

Standard models in Economics assume that rational players will seek to optimize some objective utility or profit. Current studies in behavioral Economics, acknowledging that real economic agents depart from this ideal behavior, attempt at incorporating “subjective” components in these optimization programs.

A. Jean-Marie, together with F. Cabo (Univ. Valladolid) and M. Tiball (INRAe), have considered this question in the context of private contribution to a public good. The standard situation is that selfish players will not find optimal to contribute. However, players may exhibit a positional behavior (they get joy from contributing more than their opponent, and displeasure from contributing less), or a conformist behavior (the closer to the average they are, the happier they are). In that case, their private optimum may lead to a postitive contribution to the public good. The paper 45, 54 considers the case of two positional players. Nash equilibria of the static game are computed and their dependence on the parameters of the problem is thoroughly studied. A dynamic model of myopic players featuring inertia is also built. It is shown that inertia can lead to an overshooting behavior: players may contribute more than what they would at the equilibrium, for some periods of time. Preliminary results for the case where one player is positional and the other one conformist, are presented in 44

7.4.5 Stackelberg games

M. Datar and E. Altman in collaboration with H. Le Cadre (Inria team Inocs), consider in 21 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, who relies on network slicing. The authors model the interactions between the end users (followers) and the ASPs (leaders) as a Stackelberg game. The authors show that the competition between the ASPs results in a multi-resource Tullock rent-seeking game. To determine resource pricing and allocation, the authors devise two market mechanisms. First, it is assumed that the ASPs are pre-assigned with fixed shares (budgets) of infrastructure, and rely on a trading post mechanism to allocate the resource. Under this mechanism, the ASPs can redistribute their budgets in bids and customize their allocations to maximize their profits. In case a single resource is considered, it is proved that the ASPs' coupled decision problems give rise to a unique Nash equilibrium. Second, when ASPs have no bound on their budget, the problem is formulated as a pricing game with coupling constraints capturing the shared resource finite capacities, and the market prices are derived as the duals of the coupling constraints. In addition, it is proved that the pricing game admits a unique variational equilibrium. The authors implement two online learning algorithms to compute solutions of the market mechanisms. A third fully distributed algorithm based on a proximal method is proposed to compute the Variational equilibrium solution of the pricing game. Finally, the authors run numerical simulations to analyse the market mechanism's economic properties and the convergence rates of the algorithms.

7.4.6 Learning Correlated Equilibria

In 33, O. Boufous (Orange Labs and Avignon Univ.) R. El-Azouzi (LIA, Avignon Univ.), M. Touati, M. Bouhtou (both from Orange labs) together with E. Altman, consider the problem of learning a correlated equilibrium of a finite non-cooperative game and show a new adaptive heuristic, called Correlated Perturbed Regret Minimization (CPRM) for this purpose. CPRM combines regret minimization to approach the set of correlated equilibria and a simple device suggesting actions to the players to further stabilize the dynamics. Numerical experiments support the hypothesis of the pointwise convergence of the empirical distribution over action profiles to an approximate correlated equilibrium with all players following the devices' suggestions. Additional simulation results suggest that CPRM is adaptive to changes in the game such as departures or arrivals of players.

7.5.1 Caching

7.5.2 Quantum Communications

In 25 P. Nain in collaboration with G. Vardoyan (QuTech, TU Delft, The Netherlands), S. Guha (Univ. Arizona, Tucson) and D. Towsley (Univ. Massachusetts, Amherst), studies the performance of a quantum switch that distributes tripartite entangled states to sets of users. The entanglement switching process requires two steps: first, each user attempts to generate bipartite entanglement between itself and the switch; and second, the switch performs local operations and a measurement to create multipartite entanglement for a set of three users. A simple variant of this system is studied, wherein the switch has infinite memory and the links that connect the users to the switch are identical. This problem formulation is of interest to several distributed quantum applications, while the technical aspects of this work result in new contributions within queueing theory. The state of the system is modeled as continuous time Markov chain and performance metrics of interest (probability of an empty system, switch capacity, expectation and variance of the number of qubit-pairs stored) are computed via the solution of a two-dimensional functional equation obtained by reducing it to a boundary value problem on a closed curve.

7.5.3 Coordinated Iterative Water-Filling Algorithms

In 37, S. Perlaza in collaboration with M. Haddad (Univ. d’Avignon), P. Wiecek (Wrocław Univ. of Science and Technology), O. Habachi (Univ. Clermont Auvergne), and S.M. Shah (National Institute of Technology, Srinagar, India) consider a perfect coordinated water-filling game, in which each user transmits solely on a given carrier. The main goal of the proposed algorithm (FEAT) is to achieve close to optimal performance, while keeping a given level of fairness. The key idea within FEAT is to minimize the ratio between the best and the worst utilities of the users. This is done by ensuring that, at each iteration (channel assignment), a user is satisfied with this assignment as long as it does not lose much more than other users in the system. It has been shown that FEAT outperforms most of the related algorithms in many aspects, especially in interference-limited systems. Indeed, with FEAT we can ensure a near-optimal, fair and energy efficient solution with low computational complexity. In terms of robustness, it turns out that the balance between being nearly globally optimal and good from an individual point of view seems hard to sustain with a significant number of users. Also notice that, in this regard, global optimality gets less affected than the individual one, which offers hope that such an accurate water-filling algorithm can be designed around competition in interference-limited systems.

7.5.4 Simultaneous Information and Energy Transmission with Finite Constellations

Battery dependency is a critical issue when communications systems are deployed in hard-to-reach locations, e.g., remote geographical areas, concrete structures, human bodies, or disaster/war zones. In this case, the lifetime of the electronic devices or even the whole communications system is determined by the battery life. An effective remedy is using energy harvesting technologies. Specifically, energy can be harvested from different ambient sources such as light, vibrations, heat, chemical reactions, physiological processes, or the radio frequency (RF) signals produced by other communications systems. This observation rises the idea of simultaneous information and energy transmission (SIET) via RF. In 43 and 60, S. Perlaza, E. Altman and S. ul-Zuhra in collaboration with H. V. Poor (Princeton Univ.) and M. Skoglund (KTH) characterized an achievable information-energy region of simultaneous information and energy transmission over an additive white Gaussian noise channel. This analysis is performed in the finite block-length regime with finite constellations. More specifically, a method for constructing a family of codes is proposed and the set of achievable tuples of information rate, energy rate, decoding error probability (DEP) and energy outage probability (EOP) is characterized. Using existing converse results, it is shown that the construction is information rate, energy rate, and EOP optimal. The achieved DEP is, however, sub-optimal.

7.5.5 Evaluation and optimization in 5G and 6G

In 36, A. Dejonghe (Orange Labs and Avignon Univ.), Z. Altman, (Orange Labs), F. de Pellegrini (Avignon Univ.) and E. Altman, consider the problem of the integration of RIS elements in upcoming 6G networks. This paper introduces a new link-layer scheme for RIS-enabled communications building on existing models for the physical layer of RIS technologies. The scheme is able to integrate the selection of precoders/beams in a codebook and scheduling of UEs at once. Furthermore, elements for the integration of the proposed scheme in current 3GPP-5G specifications are addressed. The scheduler combines a slow mechanism operating at the downlink OFDMA frame scale with a standard proportional fair scheduler operating at the OFDMA slot scale and accommodating both LOS and nonLOS UEs. The authors introduce an optimization framework for the proposed scheduler whose performance is hence simulated in a reference scenario. The spectral efficiency figures in their tests confirm a large gain of the scheme against a baseline direct path scheme. Finally, the scheduler optimization permits to achieve a further improvement of 15-20% for non line-of-sight users.

7.5.6 Multi Resource Allocation for Network Slices with Multi-Level fairness

To satisfy demanding quality of service requirements for slice tenants and their end-users, Infrastructure Providers (InPs) need to perform efficient resource allocation. In the context of network slicing, the key challenge is the presence of multiple resource types and competing service providers (SPs) with heterogeneous characteristics and preferences. The main goal in this context is devising efficient mechanisms to create slices while ensuring fairness both among slice tenants as well as across their end-users. To address the aforementioned challenges, M. Datar, N. Modina, R. El-Azouzi and F. de Pellegrini (Avignon Univ.) formulate in 39 the multi-resource allocation for network slicing in the form of a Fisher Market model, where SPs act as buyers and a set of resources (divisible goods) is made available by the InP at different locations. Within the Fisher market framework, a generalized alpha-fairness resource allocation for SPs able to adapt the degree of fairness as a function of a nonnegative parameter alpha, striking the trade-off between fairness and efficiency. Given the resource prices, each SP with a certain budget – namely the market power of the SP – buys the optimal set of multi-resources to maximize its utility under the budget constraints. The Market Equilibrium is computed as a price vector for each resource type that ensures market clearance, i.e., the demand of a resource equals its supply. In this paper, it is shown that it is possible to let such market equilibrium correspond to the allocations maximizing alpha-fair utility, which is obtained under non-linear pricing. Furthermore, the authors obtain a closed-form of the pricing as a function of alpha and resources purchased by SP.

8.1.1 ADR Nokia on the topic “Rethinking the network: virtualizing network functions, from middleboxes to application” (October 2017 – February 2022)

Participants: Sara Alouf, Gabriele Castellano, Giovanni Neglia.

• Contractor: Nokia Bell Labs
• Collaborators: Fabio Pianese, Tianzhu Zhang

A growing number of network infrastructures are being presently considered for a software-based replacement: these range from fixed and wireless access functions to carrier-grade middle boxes and server functionalities. On the one hand, performance requirements of such applications call for an increased level of software optimization and hardware acceleration. On the other hand, customization and modularity at all layers of the protocol stack are required to support such a wide range of functions. In this scope the ADR focuses on two specific research axes: (1) the design, implementation and evaluation of a modular NFV architecture, and (2) the modelling and management of applications as virtualized network functions. Our interest is in low-latency machine learning prediction services and in particular how the quality of the predictions can be traded off with latency. The postdoc of G. Castellano was funded by this project.

8.1.2 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.

8.1.3 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.

8.1.4 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. The PhD thesis of C. Kaplan is funded by this project.

8.1.5 MyDataModels contract on the topic “Semi-supervised variational autoencoders for versatile data” (June 2019 – May 2022)

Participants: Konstantin Avrachenkov, Mikhail Kamalov.

• Contractor: MyDataModels
• Collaborators: Denis Bastiment, Aurélie Boisbunon

Variational autoencoders are highly flexible machine learning techniques for learning latent dimension representation. This model is applicable for denoising data as well as for classification purposes. In this thesis we plan to add semi-supervision component to the variational autoencoder techniques. We plan to develop methods which are universally applicable to versatile data such as categorical data, images, texts, etc. Initially starting from static data we aim to extend the methods to time-varying data such as audio, video, time-series, etc. The proposed algorithms can be integrated into the internal engine of MyDataModels company and tested on use cases of MyDataModels. This contract financed the PhD candidate M. Kamalov. His thesis was defended in December 2022.

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

9.1.2 Participation in other International Programs

9.2.1 Visits of international scientists

9.2.2 Visits to international teams

9.3.1 H2020 projects

AO BPI/PLR/PIA 5G Events Lab

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

• 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.

ANR PARFAIT

Participants: Eitan Altman, 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.

ANR MAESTRO5G

Participant: Eitan Altman.

• Project Acronym:
  MAESTRO5G
• Project Title:
  MAnagEment of Slices in The Radio access Of 5G networks
• Coordinator:
  Orange Labs
• Duration:
  February 2019 – January 2022
• Other Partners:
  Nokia Bell Labs, U. Avignon, Inria Project-Team Agora, Sorbonne U., Telecom SudParis, CentraleSupélec.
• Abstract:
  The project develops enablers for implementing and managing slices in the 5G radio access network, not only for the purpose of serving heterogeneous services, but also for dynamic sharing of infrastructure between operators. MAESTRO-5G develops a framework for resource allocation between slices and a business layer for multi-tenant slicing. It provides an orchestration framework based on Software Define Networking that manages resources and virtual functions for slices. A hardware demonstrator brings the slicing concept to reality and showcases the project’s innovations.

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: Alain Jean-Marie, Samir Medina Perlaza, Ke Sun.

• Project Acronym:
  IDEM
• Project Title:
  Information and Decision Making
• Coordinators:
  Samir Medina 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

• S. Alouf
  has delivered the following talks:

  • "Analyzing Count-Min Sketch with Conservative Updates" at
    • WIOPT 2022, Turin, Italy on September 20th
    • 12ème Atelier d'Evaluation de Performances, Grenoble, France, on July 4th
• K. Avrachenkov
  has delivered the following talks:

  • “Quantum (random) walks” at
    • Workshop “Mathematics for Quantum Technologies”, Nice, March 4
    • UCA QuantAzur days, Nice, June 16-17
• A. Jean-Marie
  delivered the talk “Préchargement dans un monde dynamique”, 12ème Atelier d'Evaluation de Performances, Grenoble, France, on July 5th
• P. Nain
  has delivered the following talks:

  • “Modeling and Performance Evaluation of a Quantum Switch”
    • as a keynote lecture at Mascots 2022, Nice, Oct. 18-20
    • as a talk at QuantAzur Days, Nice July 16-17
    • 12ème Atelier d'Evaluation de Performances, Grenoble, France, on July 4th
• G. Neglia
  delivered a talk on "Addressing Heterogeneity in Federated Learning", IMT Webinaire Data&IA, online, 23/6/2022.
• S. Perlaza
  has delivered the following talks:

  • “Empirical Risk Minimization and Zero-Sum Games with Noisy Observations” at
    • Conservatoire national des arts et métiers (CNAM), Paris, France, December 12 2022. Host: Prof. Stefano Secci.
    • Industrial Engineering and Operations Research Department. Indian Institute of Technology at Bombay (IITB), Mumbai, India, November 9 2022. Host: Prof. Manjesh Hanawal.
  • “The Role of Relative Entropy in Supervised Machine Learning”
    • Electrical and Computer Engineering Department and Center for Statistics and Machine learning at Princeton Univ., Princeton NJ USA. July 28, 2022. Host: Prof. H. Vincent Poor
    • Electrical and Computer Engineering Department at Rensselaer Polytechnic Institute, Troy NY USA. July 26, 2022. Host: Prof. Ali Tajer.
    • Laboratoire Traitement et Communication de l'Information (LTCI), TelecomParis, Saclay, France. July 6, 2022. Host: Prof. Michèle Wigger.

10.1.5 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;
  • is a member of the Conference Advisory committee of ACM SIGMETRICS;
  • was a member of the Rising Star Award Committee for ACM SIGMETRICS 2022.
• K. Avrachenkov
  • 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, from Jan 1, 2022 until Dec 31, 2023.
  • is a member of the Sharing Teaching Resources Ad Hoc Committee of the IEEE Information Theory Society.

10.1.6 Research administration

• S. Alouf
  • 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
  • is 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
• S. Perlaza
  • was a reviewer for the selection committee of Ph.D. Grants for Labex DigiCosme. Université Paris-Saclay, Saclay, France.

10.2.1 Teaching

Note: UCA is the Univ Côte d'Azur.

10.2.2 Supervision

10.2.3 Juries

10.3.1 Interventions

S. Alouf met and discussed with two classes at Jules Ferry High School in Cannes on 9 May 2022, in the context of the French national program « 1 Scientifique – 1 Classe, Chiche ! ».

International journals

• 13 articleK.Konstantin Avrachenkov, V. S.Vivek S Borkar, S.Sharayu Moharir and S. M.Suhail Mohmad Shah. Dynamic social learning under graph constraints.IEEE Transactions on Control of Network Systems93September 2022, 1435-1446
  HALDOIback to text
• 14 articleK. E.Konstantin E Avrachenkov and V.Vivek Borkar. Whittle index based Q-learning for restless bandits with average reward.Automatica139May 2022, 110186
  HALDOIback to text
• 15 articleK.Konstantin Avrachenkov, P.Patrick Brown and N.Nelly Litvak. Red Light Green Light Method for Solving Large Markov Chains.Journal of Scientific Computing9318August 2022, 43
  HALDOIback to text
• 16 articleK.Konstantin Avrachenkov, V.Vladimir Gaitsgory and L.Lucas Gamertsfelder. LP Based Upper and Lower Bounds for Cesàro and Abel Limits of the Optimal Values in Problems of Control of Stochastic Discrete Time Systems.Journal of Mathematical Analysis and Applications5121August 2022, 126121
  HALDOIback to text
• 17 articleK.Konstantin Avrachenkov, K.Kishor Patil and G.Gugan Thoppe. Online algorithms for estimating change rates of web pages.Performance Evaluation153February 2022, 25
  HALDOIback to text
• 18 articleK.Konstantin Avrachenkov. Stability and partial instability of multi-class retrial queues.Queueing Systems1003-4April 2022, 177-179
  HALDOIback to text
• 19 articleY.Younes Ben Mazziane, S.Sara Alouf and G.Giovanni Neglia. Analyzing Count Min Sketch with Conservative Updates.Computer Networks217August 2022, 109315
  HALDOIback to text
• 20 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 Control2023
  HALDOI
• 21 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 Management2022
  HALDOIback to text
• 22 articleS.Swapnil Dhamal, T.Tijani Chahed, E.Eitan Altman, A.Albert Sunny, S.Sudheer Poojary and W.Walid Ben-Ameur. Strategic investments in distributed computing: A stochastic game perspective.Journal of Parallel and Distributed Computing169November 2022, 317-333
  HALDOIback to text
• 23 articleR.Ranbir Dhounchak, V.Veeraruna Kavitha and E.Eitan Altman. Viral Marketing Branching Processes.Computer Communications198January 2023, 140-156
  HALDOI
• 24 articleM.Mounia Hamidouche, L.Laura Cottatellucci and K. E.Konstantin E Avrachenkov. On the Normalized Laplacian Spectra of Random Geometric Graphs.Journal of Theoretical ProbabilityFebruary 2022
  HALDOIback to text
• 25 articleP.Philippe Nain, G.Gayane Vardoyan, S.Saikat Guha and D.Don Towsley. Analysis of a Tripartite Entanglement Distribution Switch.Queueing Systems1013-4August 2022, 291-328
  HALDOIback to text
• 26 articleN. K.Nitish K Panigrahy, P.Philippe Nain, G.Giovanni Neglia and D.Don Towsley. A New Upper Bound on Cache Hit Probability for Non-Anticipative Caching Policies.ACM Transactions on Modeling and Performance Evaluation of Computing Systems72-4December 2022
  HALDOI
• 27 articleA.Anirudh Sabnis, T. S.Tareq Si Salem, G.Giovanni Neglia, M.Michele Garetto, E.Emilio Leonardi and R.Ramesh Sitaraman. GRADES: Gradient Descent for Similarity Caching.IEEE/ACM Transactions on Networking2022, 1-12
  HALDOIback to text
• 28 articleT. S.Tareq Si Salem, G.Giovanni Neglia and D.Damiano Carra. Ascent Similarity Caching with Approximate Indexes.IEEE/ACM Transactions on Networking2022, 1
  HALDOIback to text
• 29 articleA.Augusto Sales de Queiroz, G.Guilherme Sales Santa Cruz, A.Alain Jean-Marie, D.Dorian Mazauric, J.Jérémie Roux and F.Frédéric Cazals. Gene prioritization based on random walks with restarts and absorbing states, to define gene sets regulating drug pharmacodynamics from single-cell analyses.PLoS ONE1711November 2022, e0268956
  HALDOIback to text
• 30 articleT.Tareq Si Salem, G.Georgios Iosifidis and G.Giovanni Neglia. Enabling Long-term Fairness in Dynamic Resource Allocation.Proceedings of the ACM on Measurement and Analysis of Computing Systems 63December 2022, 1-36
  HALDOIback to text

International peer-reviewed conferences

• 31 inproceedingsY.Younes Ben Mazziane, S.Sara Alouf and G.Giovanni Neglia. A Formal Analysis of the Count-Min Sketch with Conservative Updates.IEEE INFOCOM WNA 2022 - The second Workshop on Networking Algorithms (WNA)New York, United StatesMay 2022
  HALDOIback to text
• 32 inproceedingsY.Younes Ben Mazziane, S.Sara Alouf, G.Giovanni Neglia and D.Daniel Sadoc Menasche. Computing the Hit Rate of Similarity Caching.IEEE Global Communications Conference (GLOBECOM)Rio de Janeiro, BrazilDecember 2022, 141-146
  HALDOIback to text
• 33 inproceedingsO.Omar Boufous, R.Rachid El-Azouzi, M.Mikaël Touati, E.Eitan Altman and M.Mustapha Bouhtou. Learning a Correlated Equilibrium with Perturbed Regret Minimization.EAI VALUETOOLS 2022 - 15th EAI International Conference on Performance Evaluation Methodologies and ToolsGhent, BelgiumNovember 2022
  HALback to text
• 34 inproceedingsG.Gabriele Castellano, F.Fabio Pianese, D.Damiano Carra, T.Tianzhu Zhang and G.Giovanni Neglia. Regularized Bottleneck with Early Labeling.ITC 2022 - 34th International Teletraffic CongressShenzhen, ChinaSeptember 2022
  HALback to text
• 35 inproceedingsO.Olga Chuchuk, G.Giovanni Neglia, M.Markus Schulz and D.Dirk Duellmann. Caching for dataset-based workloads with heterogeneous file sizes.ISGC 2022 - International Symposium on Grids & Clouds 2022Taipei, Taiwan2022
  HALback to text
• 36 inproceedingsA.Antoine Dejonghe, Z.Zwi Altman, F.Francesco de Pellegrini and E.Eitan Altman. A Lightweight Joint RIS/BS Configuration Scheme.6GNet 2022 - 1st International conference on 6G NetworkingParis, FranceJuly 2022
  HALback to text
• 37 inproceedingsM.Majed Haddad, P.Piotr Wiecek, O.Oussama Habachi, S. M.Samir M. Perlaza and S.Shahid Mehraj Shah. FEAT: Fair Coordinated Iterative Water-Filling Algorithm.MSWIM'22 - 25th International Conference on Modeling, Analysis and Simulation of Wireless and Mobile SystemsMontreal, CanadaOctober 2022
  HALback to text
• 38 inproceedingsO.Othmane Marfoq, L.Laetitia Kameni, R.Richard Vidal and G.Giovanni Neglia. Personalized Federated Learning through Local Memorization.ICML - 39th International Conference on Machine Learning162Baltimore (Maryland), United StatesJuly 2022
  HALback to text
• 39 inproceedingsN.Naresh Modina, M.Mandar Datar, R.Rachid El-Azouzi and F.Francesco de Pellegrini. Multi Resource Allocation for Network Slices with Multi-Level fairness.IEEE International Conference on Communications (ICC)Seoul (Korea), South KoreaMay 2022
  HALback to text
• 40 inproceedingsS. 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: Optimality and Sensitivity Analysis.ISIT 2022 - IEEE International Symposium on Information TheoryEspoo, FinlandJune 2022, 684-689
  HALDOIback to text
• 41 inproceedingsJ. O.Jean Ogier Du Terrail, S.-S.Samy-Safwan Ayed, E.Edwige Cyffers, F.Felix Grimberg, C.Chaoyang He, R.Regis Loeb, P.Paul Mangold, T.Tanguy Marchand, O.Othmane Marfoq, E.Erum Mushtaq, B.Boris Muzellec, C.Constantin Philippenko, S.Santiago Silva, M.Maria Teleńczuk, S.Shadi Albarqouni, S.Salman Avestimehr, A.Aurélien Bellet, A.Aymeric Dieuleveut, M.Martin Jaggi, S. P.Sai Praneeth Karimireddy, M.Marco Lorenzi, G.Giovanni Neglia, M.Marc Tommasi and M.Mathieu Andreux. FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings.NeurIPS 2022 - Thirty-sixth Conference on Neural Information Processing SystemsProceedings of NeurIPSNew Orleans, United StatesNovember 2022
  HALback to text
• 42 inproceedingsS.Sadaf Ul Zuhra, S. M.Samir M Perlaza, H. V.H Vincent Poor and M.Mikael Skoglund. Information-Energy Trade-offs with EH Non-linearities in the Finite Block-Length Regime with Finite Constellations.ITW 2022 - IEEE Information Theory WorkshopMumbai, IndiaNovember 2022, 55-60
  HALDOI
• 43 inproceedingsS. U.Sadaf Ul Zuhra, S. M.Samir M. Perlaza, H. V.H. Vincent Poor and E.Eitan Altman. Achievable Information-Energy Region in the Finite Block-Length Regime with Finite Constellations.ISIT 2022 - IEEE International Symposium on Information TheoryEspoo, FinlandJune 2022, 2106-2111
  HALDOIback to text

Conferences without proceedings

• 44 inproceedingsF.Francisco Cabo, A.Alain Jean-Marie and M.Mabel Tidball. Positional and conformist effects in public good provision. Strategic interaction and inertia.19th International Symposium on Dynamic Games and ApplicationsPorto, PortugalJuly 2022
  HALback to text
• 45 inproceedingsF.Francisco Cabo, A.Alain Jean-Marie and M.Mabel Tidball. Positional effects in public good provision. Strategic interaction and inertia.19th International Symposium on Dynamic Games and ApplicationsPorto, PortugalJuly 2022
  HALback to text
• 46 inproceedingsI.Ilias Driouich, C.Chuan Xu, G.Giovanni Neglia, F.Frederic Giroire and E.Eoin Thomas. A Novel Model-Based Attribute Inference Attack in Federated Learning.FL-NeurIPS'22 - Federated Learning: Recent Advances and New Challenges workshop in Conjunction with NeurIPS 2022New orleans, United StatesDecember 2022
  HALback to text
• 47 inproceedingsK.Kausthub Keshava, A.Alain Jean-Marie and S.Sara Alouf. Optimisation du préchargement dans un monde dynamique.ROADEF 2022 - 23ème congrès annuel de la Société Française de Recherche Opérationnelle et d'Aide à la DécisionVilleurbanne - Lyon, FranceFebruary 2022
  HAL
• 48 inproceedingsF.Francisco Robledo, V. S.Vivek S Borkar, U.Urtzi Ayesta and K.Konstantin Avrachenkov. Tabular and Deep Learning of Whittle Index.EWRL 2022 - 15th European Workshop of Reinforcement LearningMilan, ItalySeptember 2022
  HALback to text

Scientific books

• 49 bookK.Konstantin Avrachenkov and M.Maximilien Dreveton. Statistical Analysis of Networks.Now PublishersOctober 2022
  HALDOIback to textback to text

Doctoral dissertations and habilitation theses

• 50 thesisM.Mandar Datar. Resource Allocation and Pricing in 5G Network Slicing.Université d'AvignonJune 2022
  HALback to text
• 51 thesisM.Maximilien Dreveton. Graph clustering and semi-supervised learning of non-binary, temporal and geometric networks.Université Côte d'AzurApril 2022
  HALback to text
• 52 thesisM.Mikhail Kamalov. Scalable algorithms for graph-based semi-supervised learning with embedding.Université Côte d'AzurDecember 2022
  HAL
• 53 thesisT.Tareq Si Salem. Online learning for network resource allocation.Université Côte d'AzurOctober 2022
  HALback to text

Reports & preprints

• 54 miscF.Francisco Cabo, A.Alain Jean-Marie and M.Mabel Tidball. Positional effects in public good provision. Strategic interaction and inertia.April 2022, 50 p..
  HALback to text
• 55 reportS. M.Samir M. Perlaza, G.Gaetan Bisson, I.Iñaki Esnaola, A.Alain Jean-Marie and S.Stefano Rini. Empirical Risk Minimization with Generalized Relative Entropy Regularization.RR-9454InriaFebruary 2022
  HALback to text
• 56 miscS. M.Samir M Perlaza, G.Gaetan Bisson, I.Iñaki Esnaola, A.Alain Jean-Marie and S.Stefano Rini. Empirical Risk Minimization with Generalized Relative Entropy Regularization.November 2022
  HALback to text
• 57 reportS. M.Samir M. Perlaza, I.Iñaki Esnaola and H.H Vincent Poor. Sensitivity of the Gibbs Algorithm to Data Aggregation in Supervised Machine Learning.RR-9474InriaJune 2022, 22
  HALback to text
• 58 reportK.Ke Sun, S. M.Samir M. Perlaza and A.Alain Jean-Marie. 2 × 2 Zero-Sum Games with Commitments and Noisy Observations.Inria - Sophia AntipolisMay 2023
  HALback to text
• 59 reportK.Ke Sun. Some Properties of the Nash Equilibrium in 2 × 2 Zero-Sum Games.RR-9492INRIANovember 2022
  HALback to text
• 60 miscS.Sadaf Ul Zuhra, S. M.Samir M Perlaza, H. V.H. Vincent Poor, E.Eitan Altman and M.Mikael Skoglund. Information-Energy Regions in the Finite Block-Length Regime with Finite Channel Inputs.November 2022
  HALback to text
• 61 miscX.Xiuzhen Ye, I.Iñaki Esnaola, S. M.Samir M. Perlaza and R. F.Robert F Harrison. Stealth Data Injection Attacks with Sparsity Constraints.January 2022
  HAL
• 62 reportX.Xiuzhen Ye, I.Iñaki Esnaola, S. M.Samir M. Perlaza and R. F.Robert F Harrison. Stealth Data Injection Attacks with Sparsity Constraints.RR-9481Institut National de Recherche en Informatique et en Automatique (INRIA)September 2022
  HALback to text
• 63 reportS. U.Sadaf Ul Zuhra, S. M.Samir M. Perlaza, H. V.H. Vincent Poor and E.Eitan Altman. Simultaneous Information and Energy Transmission with Finite Constellations.RR-9409Inria Sophia Antipolis - MéditerranéeJanuary 2022, 1-37
  HAL

Other scientific publications

• 64 inproceedingsF.Francisco Robledo, U.Urtzi Ayesta, K.Konstantin Avrachenkov and V. S.Vivek S Borkar. Tabular and Deep Learning of Whittle Index.EWRL 2022 - 15th European Workshop on Reinforcement LearningMilan, ItalySeptember 2022
  HALback to text
• 65 miscR.Raphaël Taisant, M.Mandar Datar, H.Hélène Le Cadre and E.Eitan Altman. Balancing Efficiency and Privacy in a Decision-Dependent Network Game.Palaiseau, FranceNovember 2022
  HAL