Bibliography

Major publications by the team in recent years

• 1O. Cappé, A. Garivier, O.-A. Maillard, R. Munos, G. Stoltz.
  Kullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation, in: Annals of Statistics, 2013, vol. 41, n^o 3, pp. 1516-1541, Accepted, to appear in Annals of Statistics.
  https://hal.archives-ouvertes.fr/hal-00738209
• 2A. Carpentier, M. Valko.
  Revealing graph bandits for maximizing local influence, in: International Conference on Artificial Intelligence and Statistics, Seville, Spain, May 2016.
  https://hal.inria.fr/hal-01304020
• 3N. Gatti, A. Lazaric, M. Rocco, F. Trovò.
  Truthful Learning Mechanisms for Multi–Slot Sponsored Search Auctions with Externalities, in: Artificial Intelligence, October 2015, vol. 227, pp. 93-139.
  https://hal.inria.fr/hal-01237670
• 4M. Ghavamzadeh, Y. Engel, M. Valko.
  Bayesian Policy Gradient and Actor-Critic Algorithms, in: Journal of Machine Learning Research, January 2016, vol. 17, n^o 66, pp. 1-53.
  https://hal.inria.fr/hal-00776608
• 5H. Kadri, E. Duflos, P. Preux, S. Canu, A. Rakotomamonjy, J. Audiffren.
  Operator-valued Kernels for Learning from Functional Response Data, in: Journal of Machine Learning Research (JMLR), 2016.
  https://hal.archives-ouvertes.fr/hal-01221329
• 6E. Kaufmann, O. Cappé, A. Garivier.
  On the Complexity of Best Arm Identification in Multi-Armed Bandit Models, in: Journal of Machine Learning Research, January 2016, vol. 17, pp. 1-42.
  https://hal.archives-ouvertes.fr/hal-01024894
• 7A. Lazaric, M. Ghavamzadeh, R. Munos.
  Analysis of Classification-based Policy Iteration Algorithms, in: Journal of Machine Learning Research, 2016, vol. 17, pp. 1 - 30.
  https://hal.inria.fr/hal-01401513
• 8R. Munos.
  From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning, 2014, 130 pages.
  https://hal.archives-ouvertes.fr/hal-00747575
• 9R. Ortner, D. Ryabko, P. Auer, R. Munos.
  Regret bounds for restless Markov bandits, in: Journal of Theoretical Computer Science (TCS), 2014, vol. 558, pp. 62-76. [ DOI : 10.1016/j.tcs.2014.09.026 ]
  https://hal.inria.fr/hal-01074077
• 10D. Ryabko, J. Mary.
  A Binary-Classification-Based Metric between Time-Series Distributions and Its Use in Statistical and Learning Problems, in: Journal of Machine Learning Research, 2013, vol. 14, pp. 2837-2856.
  https://hal.inria.fr/hal-00913240

Publications of the year

Doctoral Dissertations and Habilitation Theses

• 11H. Glaude.
  Learning rational linear sequential systems using the method of moments, Université de Lille 1 - Sciences et Technologies, July 2016.
  https://tel.archives-ouvertes.fr/tel-01374080
• 12F. Guillou.
  On Recommendation Systems in a Sequential Context, Université Lille 3, December 2016.
  https://tel.archives-ouvertes.fr/tel-01407336
• 13V. Musco.
  Propagation Analysis based on Software Graphs and Synthetic Data, Université Lille 3, November 2016.
  https://tel.archives-ouvertes.fr/tel-01398903
• 14M. Valko.
  Bandits on graphs and structures, École normale supérieure de Cachan - ENS Cachan, June 2016, Habilitation à diriger des recherches.
  https://hal.inria.fr/tel-01359757

Articles in International Peer-Reviewed Journals

• 15M. Ghavamzadeh, Y. Engel, M. Valko.
  Bayesian Policy Gradient and Actor-Critic Algorithms, in: Journal of Machine Learning Research, January 2016, vol. 17, n^o 66, pp. 1-53.
  https://hal.inria.fr/hal-00776608
• 16H. Kadri, E. Duflos, P. Preux, S. Canu, A. Rakotomamonjy, J. Audiffren.
  Operator-valued Kernels for Learning from Functional Response Data, in: Journal of Machine Learning Research (JMLR), 2016.
  https://hal.archives-ouvertes.fr/hal-01221329
• 17E. Kaufmann, O. Cappé, A. Garivier.
  On the Complexity of Best Arm Identification in Multi-Armed Bandit Models, in: Journal of Machine Learning Research, January 2016, vol. 17, pp. 1-42.
  https://hal.archives-ouvertes.fr/hal-01024894
• 18A. Khaleghi, D. Ryabko.
  Nonparametric multiple change point estimation in highly dependent time series, in: Theoretical Computer Science, 2016, vol. 620, pp. 119-133. [ DOI : 10.1016/j.tcs.2015.10.041 ]
  https://hal.inria.fr/hal-01235330
• 19A. Khaleghi, D. Ryabko, J. Mary, P. Preux.
  Consistent Algorithms for Clustering Time Series, in: Journal of Machine Learning Research, 2016, vol. 17, n^o 3, pp. 1 - 32.
  https://hal.inria.fr/hal-01399613
• 20A. Lazaric, M. Ghavamzadeh, R. Munos.
  Analysis of Classification-based Policy Iteration Algorithms, in: Journal of Machine Learning Research, 2016, vol. 17, pp. 1 - 30.
  https://hal.inria.fr/hal-01401513
• 21V. Musco, M. Monperrus, P. Preux.
  A Large-scale Study of Call Graph-based Impact Prediction using Mutation Testing, in: Software Quality Journal, 2016. [ DOI : 10.1007/s11219-016-9332-8 ]
  https://hal.inria.fr/hal-01346046
• 22G. Neu, B. Gábor.
  Importance Weighting Without Importance Weights: An Efficient Algorithm for Combinatorial Semi-Bandits, in: Journal of Machine Learning Research, August 2016, vol. 17, n^o 154, pp. 1 - 21.
  https://hal.archives-ouvertes.fr/hal-01380278

International Conferences with Proceedings

• 23K. Azizzadenesheli, A. Lazaric, A. Anandkumar.
  Reinforcement Learning of POMDPs using Spectral Methods, in: Proceedings of the 29th Annual Conference on Learning Theory (COLT2016), New York City, United States, June 2016.
  https://hal.inria.fr/hal-01322207
• 24M. Barlier, R. Laroche, O. Pietquin.
  A Stochastic Model for Computer-Aided Human-Human Dialogue, in: Interspeech 2016, San Francisco, United States, September 2016, vol. 2016, pp. 2051 - 2055.
  https://hal.inria.fr/hal-01406894
• 25M. Barlier, R. Laroche, O. Pietquin.
  Learning Dialogue Dynamics with the Method of Moments, in: Workshop on Spoken Language Technologie (SLT 2016), San Diego, United States, December 2016.
  https://hal.inria.fr/hal-01406904
• 26D. Calandriello, A. Lazaric, M. Valko.
  Analysis of Nyström method with sequential ridge leverage score sampling, in: Uncertainty in Artificial Intelligence, New York City, United States, June 2016.
  https://hal.inria.fr/hal-01343674
• 27A. Carpentier, M. Valko.
  Revealing graph bandits for maximizing local influence, in: International Conference on Artificial Intelligence and Statistics, Seville, Spain, May 2016.
  https://hal.inria.fr/hal-01304020
• 28L. El Asri, R. Laroche, O. Pietquin.
  Compact and Interpretable Dialogue State Representation with Genetic Sparse Distributed Memory, in: 7th International Workshop on Spoken Dialogue Systems (IWSDS 2016), Saariselka, Finland, January 2016.
  https://hal.inria.fr/hal-01406873
• 29L. El Asri, B. Piot, M. Geist, R. Laroche, O. Pietquin.
  Score-based Inverse Reinforcement Learning, in: International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016), Singapore, Singapore, May 2016.
  https://hal.inria.fr/hal-01406886
• 30A. Erraqabi, M. Valko, A. Carpentier, O.-A. Maillard.
  Pliable rejection sampling, in: International Conference on Machine Learning, New York City, United States, June 2016.
  https://hal.inria.fr/hal-01322168
• 31C. Z. Felício, K. V. R. Paixão, C. A. Z. Barcelos, P. Preux.
  Preference-like Score to Cope with Cold-Start User in Recommender Systems, in: 28th International Conference on Tools with Artificial Intelligence (ICTAI), San Jose, United States, Proceedings of the IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI), November 2016.
  https://hal.inria.fr/hal-01390762
• 32V. Gabillon, A. Lazaric, M. Ghavamzadeh, R. Ortner, P. Bartlett.
  Improved Learning Complexity in Combinatorial Pure Exploration Bandits, in: Proceedings of the 19th International Conference on Artificial Intelligence (AISTATS), Cadiz, Spain, May 2016.
  https://hal.inria.fr/hal-01322198
• 33A. Garivier, E. Kaufmann.
  Optimal Best Arm Identification with Fixed Confidence, in: 29th Annual Conference on Learning Theory (COLT), New York, United States, JMLR Workshop and Conference Proceedings, June 2016, vol. 49.
  https://hal.archives-ouvertes.fr/hal-01273838
• 34A. Garivier, E. Kaufmann, W. M. Koolen.
  Maximin Action Identification: A New Bandit Framework for Games, in: 29th Annual Conference on Learning Theory (COLT), New-York, United States, JMLR Workshop and Conference Proceedings, June 2016, vol. 49.
  https://hal.archives-ouvertes.fr/hal-01273842
• 35A. Garivier, E. Kaufmann, T. Lattimore.
  On Explore-Then-Commit Strategies, in: NIPS, Barcelona, Spain, Advances in Neural Information Processing Systems (NIPS), December 2016, vol. 29.
  https://hal.archives-ouvertes.fr/hal-01322906
• 36H. Glaude, O. Pietquin.
  PAC learning of Probabilistic Automaton based on the Method of Moments, in: International Conference on Machine Learning (ICML 2016), New York, United States, June 2016.
  https://hal.inria.fr/hal-01406889
• 37J.-B. Grill, M. Valko, R. Munos.
  Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning, in: NIPS 2016 - Thirtieth Annual Conference on Neural Information Processing Systems, Barcelona, Spain, December 2016.
  https://hal.inria.fr/hal-01389107
• 38F. Guillou, R. Gaudel, P. Preux.
  Large-scale Bandit Recommender System, in: the 2nd International Workshop on Machine Learning, Optimization and Big Data (MOD'16), Volterra, Italy, August 2016.
  https://hal.inria.fr/hal-01406389
• 39F. Guillou, R. Gaudel, P. Preux.
  Scalable explore-exploit Collaborative Filtering, in: Pacific Asia Conference on Information Systems (PACIS'16), Chiayi, Taiwan, 2016.
  https://hal.inria.fr/hal-01406418
• 40F. Guillou, R. Gaudel, P. Preux.
  Sequential Collaborative Ranking Using (No-)Click Implicit Feedback, in: The 23rd International Conference on Neural Information Processing (ICONIP'16), Kyoto, Japan, Lecture Notes in Computer Science, October 2016, vol. 9948, pp. 288 - 296. [ DOI : 10.1007/978-3-319-46672-9_33 ]
  https://hal.inria.fr/hal-01406338
• 41E. Kaufmann, T. Bonald, M. Lelarge.
  A Spectral Algorithm with Additive Clustering for the Recovery of Overlapping Communities in Networks, in: ALT 2016 - Algorithmic Learning Theory, Bari, Italy, R. Ortner, H. U. Simon, S. Zilles (editors), Lecture Notes in Computer Science, Springer, October 2016, vol. 9925, pp. 355-370. [ DOI : 10.1007/978-3-319-46379-7_24 ]
  https://hal.archives-ouvertes.fr/hal-01163147
• 42T. Kocák, G. Neu, M. Valko.
  Online learning with Erdős-Rényi side-observation graphs, in: Uncertainty in Artificial Intelligence, New York City, United States, June 2016.
  https://hal.inria.fr/hal-01320588
• 43T. Kocák, G. Neu, M. Valko.
  Online learning with noisy side observations, in: International Conference on Artificial Intelligence and Statistics, Seville, Spain, May 2016.
  https://hal.inria.fr/hal-01303377
• 44V. Musco, A. Carette, M. Monperrus, P. Preux.
  A Learning Algorithm for Change Impact Prediction, in: 5th International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering, Austin, United States, May 2016.
  https://hal.inria.fr/hal-01279620
• 45V. Musco, M. Monperrus, P. Preux.
  Mutation-Based Graph Inference for Fault Localization, in: International Working Conference on Source Code Analysis and Manipulation, Raleigh, United States, October 2016.
  https://hal.inria.fr/hal-01350515
• 46J. Pérolat, B. Piot, M. Geist, B. Scherrer, O. Pietquin.
  Softened Approximate Policy Iteration for Markov Games, in: ICML 2016 - 33rd International Conference on Machine Learning, New York City, United States, June 2016.
  https://hal.inria.fr/hal-01393328
• 47J. Pérolat, B. Piot, B. Scherrer, O. Pietquin.
  On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov Games, in: 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016), Cadiz, Spain, Proceedings of the International Conference on Artificial Intelligences and Statistics, May 2016.
  https://hal.inria.fr/hal-01291495
• 48D. Ryabko.
  Things Bayes can't do, in: Proceedings of the 27th International Conference on Algorithmic Learning Theory (ALT'16), Bari, Italy, October 2016, vol. LNCS, n^o 9925, pp. 253-260. [ DOI : 10.1007/978-3-319-46379-7_17 ]
  https://hal.inria.fr/hal-01380063
• 49F. Strub, R. Gaudel, J. Mary.
  Hybrid Recommender System based on Autoencoders, in: the 1st Workshop on Deep Learning for Recommender Systems, Boston, United States, September 2016, pp. 11 - 16. [ DOI : 10.1145/2988450.2988456 ]
  https://hal.inria.fr/hal-01336912
• 50A. C. Y. Tossou, C. Dimitrakakis.
  Algorithms for Differentially Private Multi-Armed Bandits, in: AAAI 2016, Phoenix, Arizona, United States, February 2016.
  https://hal.inria.fr/hal-01234427
• 51Z. Zhang, B. Rubinstein, C. Dimitrakakis.
  On the Differential Privacy of Bayesian Inference, in: AAAI 2016, Phoenix, Arizona, United States, February 2016.
  https://hal.inria.fr/hal-01234215

Conferences without Proceedings

• 52A. Bérard, C. Servan, O. Pietquin, L. Besacier.
  MultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP, in: The 10th edition of the Language Resources and Evaluation Conference (LREC), Portoroz, Slovenia, May 2016.
  https://hal.archives-ouvertes.fr/hal-01335930
• 53F. Guillou, R. Gaudel, P. Preux.
  Compromis exploration-exploitation pour système de recommandation à grande échelle, in: Conférence francophone sur l'Apprentissage Automatique (CAp'16), Marseille, France, July 2016.
  https://hal.inria.fr/hal-01406439
• 54F. Strub, J. Mary, R. Gaudel.
  Filtrage Collaboratif Hybride avec des Auto-encodeurs, in: Conférence francophone sur l'Apprentissage Automatique (CAp'16), Marseille, France, July 2016.
  https://hal.inria.fr/hal-01406432

Internal Reports

• 55B. Danglot, P. Preux, B. Baudry, M. Monperrus.
  Correctness Attraction: A Study of Stability of Software Behavior Under Runtime Perturbation, HAL, 2016, n^o hal-01378523.
  https://hal.archives-ouvertes.fr/hal-01378523

Other Publications

• 56S. Bubeck, R. Eldan, J. Lehec.
  Sampling from a log-concave distribution with Projected Langevin Monte Carlo, January 2017, working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-01428950
• 57C. Dimitrakakis, F. Jarboui, D. Parkes, L. Seeman.
  Multi-view Sequential Games: The Helper-Agent Problem, December 2016, working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-01408294
• 58E. Kaufmann.
  On Bayesian index policies for sequential resource allocation, September 2016, working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-01251606
• 59A. R. Luedtke, E. Kaufmann, A. Chambaz.
  Asymptotically Optimal Algorithms for Multiple Play Bandits with Partial Feedback, June 2016, working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-01338733
• 60F. Strub, J. Mary, R. Gaudel.
  Hybrid Collaborative Filtering with Autoencoders, July 2016, working paper or preprint.
  https://hal.archives-ouvertes.fr/hal-01281794

References in notes

• 61P. Auer, N. Cesa-Bianchi, P. Fischer.
  Finite-time analysis of the multi-armed bandit problem, in: Machine Learning, 2002, vol. 47, n^o 2/3, pp. 235–256.
• 62R. Bellman.
  Dynamic Programming, Princeton University Press, 1957.
• 63D. Bertsekas, S. Shreve.
  Stochastic Optimal Control (The Discrete Time Case), Academic Press, New York, 1978.
• 64D. Bertsekas, J. Tsitsiklis.
  Neuro-Dynamic Programming, Athena Scientific, 1996.
• 65M. Puterman.
  Markov Decision Processes: Discrete Stochastic Dynamic Programming, John Wiley and Sons, 1994.
• 66H. Robbins.
  Some aspects of the sequential design of experiments, in: Bull. Amer. Math. Soc., 1952, vol. 55, pp. 527–535.
• 67R. Sutton, A. Barto.
  Reinforcement learning: an introduction, MIT Press, 1998.
• 68P. Werbos.
  ADP: Goals, Opportunities and Principles, IEEE Press, 2004, pp. 3–44, Handbook of learning and approximate dynamic programming.