Talks

International Conference and Seminar

  1. Bandits in Auctions. New perspectives in sequential learning, Applied Math Seminar, Santiago de Chile (2016)

  2. Online Learning and Repeated Auctions, International Conference on Game Theory, Stony Brook (2016)

  3. Highly-Smooth Zero-th Order Online Optimization, Statistical seminar of KTH, Stockholm (2016)

  4. Highly-Smooth Zero-th Order Online Optimization, Conference on Learning Theory, New York (2016)

  5. Online Learning and Blackwell Approachability in Quitting Games, Conference on Learning Theory, New York (2016)

  6. Highly-Smooth Zero-th Order Online Optimization, AdGo 2016 Workshop, Chili (2016)

  7. Approachability in Absorbing Games, Conference on Optimization & Practices in Industry (PGMO-COPI), Polytechnique, France, (2015)

  8. Highly-Smooth Zero-th Order Online Optimization, Cambridge, UK (2015)

  9. Highly-Smooth Zero-th Order Online Optimization, Machine Learning Thematic Semester, Toulouse, France (2015)

  10. Online Learning, Individual Sequences and Game Theory: Beyond Regret Minimization and Game Theory, 5 hours course, Toulouse, France (2015)

  11. Bandit Problems & Ethical Clinical Trials Optimal Sample Size in Multi-Phase Online Learning, Stochastic and Statistic Seminar, MIT, USA (2015)

  12. From bandits to ethical clinical trials; optimal sample size for multi-stage problems, New procedures for New Data, CIRM, France, (2014)

  13. Blackwell Approachability in Absorbing Games, Optimal Cooperation, Communication, and Learning in Decentralized Systems, Banff, Canada, (2014)

  14. Online multi-class classification via Blackwell Approachability, Conference on Optimization & Practices in Industry (PGMO-COPI), Polytechnique, France, (2014)

  15. New results in bandit problems with applications, Conference on Optimization & Practices in Industry (PGMO-COPI), Polytechnique, France, (2014)

  16. Online learning & multi-objective optimization, Conference On Learning Theory (COLT), Barcelona, Spain, (2014)

  17. Multi-armed bandit problem, Algorithms and Dynamics for Games and Optimization, Playa Blanca, Chile, (2013)

  18. Recent Advances and Applications of Blackwell’s Approachability Theory, Mathematical Statistics with Applications in Mind, CIRM, (2013)

  19. Approachability, Fast and Slow, COLT, Princeton, (2013)

  20. Exponential Weight Approachability Applications to Regret Minimization and Calibration, Stochastic Methods in Game Theory, Erice, (2013)

  21. Generalized Exponential Weight Algorithm Applications to Regret Minimization and Calibration, Workshop on Statistical Learning, Moscow, (2013)

  22. Nash Equilibria with uncertainties; Extension of Lemke Howson algorithm,Franco-Taiwanese Days, Paris, (2012)

  23. Nash Eq. and Lemke-Howson algorithm in games with uncertainties,METEOR-ETBC seminar, Maastricht, (2012)

  24. Nash Equilibria with uncertainties Extension of Lemke Howson algorithm,The 23rd International Conference on Game Theory, Stony Brook, USA, (2012)

  25. The multi-armed bandit problem with covariates, Machine Learning Seminar, Techniion, Haïfa, Israel, (2011)

  26. Purely informative game. Approachability in Wasserstein space , Conference Games Toulouse 2011, Toulouse, France, (2011)

  27. Robust approachability regret minimization with partial monitoring , Conference On Learning Theory, Budapest, Hungary, (2011)

  28. Internal regret with partial monitoring. Calibration-based optimal algorithms, Workshop on Stochastic Methods in Game Theory, Erice, Italy, (2010)

  29. Internal regret with partial monitoring. Calibration-based optimal algorithms, Workshop on Algorithmic Game Theory: Dynamics and Convergence in Distributed Systems; ICALP 2010, Bordeaux, France, (2010)

  30. Games and Approachability in the Informative Space, Dynamic Games: Discrete and Continuous Time (IV), Paris, France, (2009)

  31. Calibration and Internal no-Regret with Partial Monitoring, 20th Conference on Algorithmic Learning Theory, Porto, Portugal, (2009)

  32. Direct No-Regret Procedures with Random Signals, Workshop Dynamic Games, Differential Games (III), Roscoff, France, (2008)

French Conference and Seminar

  1. Parcimonie, Apprentissage Séquentiel et Optimisation en Ligne, Colloque Mastodons, Paris (2017)

  2. New Perspectives for Multi-Armed Bandits and Their Applications, Workshop Learning & Statistics, IHES (2017)

  3. Online Learning & Game Theory Repeated Auctions, Journées SMAI-Mode 2016, Toulouse (2016)

  4. Highly-Smooth Zero-th Order Online Optimization, Stochastic algorithms for big data, UPMC, Paris (2016)

  5. Multi-Armed Bandit Problems, 4h course, Mascot Num, Toulouse (2016)

  6. Online Learning & Repeated Auctions, Séminaire Sequel, INRIA Lille (2016)

  7. Highly-Smooth Zero-th Order Online Optimization, Computational and Statistical Trade-Offs in Learning, IHES (2016)

  8. Multi-armed bandits & repeated auctions, Geometry, Evolution and Learning, Luchon (2016)

  9. Regret Minimization meets Repeated Auctions, Séminaire du DI, ENS Paris (2016)

  10. An overview of “Bandit Problems”, DeMagma Workshop, Paris (2016)

  11. Highly-Smooth Zero-th Order Online Optimization, Canum, Obernay (2016)

  12. Highly-Smooth Zero-th Order Online Optimization, ML semester Workshop, Toulouse (2015)

  13. Optimal Sample Size in Multi-Phase Learning, Séminaire du LRI, Paris Sud (2015)

  14. Optimal Sample Size for Multi-Phase Online Learning Problems, Séminaire du LIAFA, Paris Diderot (2015)

  15. Bandit Problems & Ethical Clinical Trials Optimal Sample Size in Multi-Phase Online Learning, Semestre du CIMI, Toulouse, (2015)

  16. Stochastic Bandit Optimization Theoretical vs (more) Realistic worlds, Séminaire de Statistiques, Grenoble, (2015)

  17. From bandits to ethical clinical trials; optimal sample size for multi-stage problems, Congrès SMAI, les Karellis, (2014)

  18. Bandit Problems & Ethical Clinical Trials Optimal Sample Size in Multi-Phase Online Learning, Séminaire du CMAP, Polytechnique, (2015)

  19. Optimal Sample Size in Multi-Phase Learning, Séminaire LRI, Orsay, (2015)

  20. Online Learning and Optimization in adversarial environment, Séminaire Beer & Tech Criteo, Paris, (2015)

  21. Bandits problems with medical applications (motivations) and open problems, MLDMA group seminar, Cachan, (2015)

  22. Optimal Sample Size for Multi-Phase Online Learning Problems, LIAFA seminar, Paris, (2015)

  23. From bandits to ethical clinical trials; optimal sample size for multi-stage problems, Séminaire de Paris Sud, Orsay, (2014)

  24. An overview of Bandits Problems, Sierra-Willow group meeting, Inria Paris, (2014)

  25. On computation and characterization of Nash equilibria with uncertainties using the Lemke-Howson algorithm , Worskhop ambiguity, Paris School of Economics, (2014)

  26. On equilibria in robust games: existence, characterization and computation , PGMO monthly seminar, Ecole Polytechnique, (2014)

  27. Regret Minimization and Calibration Through Blackwell Approachability, Smile, Paris, (2013).

  28. Blackwell’s approachability: a geometric tool and its application to regret minimization, Conférence de la SMAI, (2013)

  29. Multi-armed bandit with covariates, Toulouse School of Economics, (2013)

  30. Weak Approachability in Wasserstein Space, Jeux dynamics jeux différentiels, Roscoff, (2013)

  31. Nash Eq. and Lemke-Howson algorithm in games with uncertainties, Séminaire Ecole Nationale des Ponts et Chaussées, (2013)

  32. The multi-armed bandit with covariates, Séminaire Algorithmes et Complexité, LIAFA, Université Paris Diderot, (2013)

  33. The multi-armed bandit with covariates, Séminaire d’Analyse, Phénomènes Stochastiques et Applications, Brest, (2013)

  34. The multi-armed bandit problem with covariates, Modal’X Seminar, Nanterre, France, (2011)

  35. Robust Approachability controlled random walks with uncertainties, Seminar of "Laboratoire de Probabilités et Modèles Aléatoires, Paris, France, (2011)

  36. The multi-armed bandit problem with covariates, Parisian Seminar of Statistics, Paris, France, (2011)

  37. On-line learning with partial monitoring, Seminar "Statistics, Analysis and Multi-disciplinary Modelization", Paris, France, (2011)

  38. Regret and convergence to equilibria: applications and generalizations, Journée du Laboratoire de Recherche Informatique "Jeux Matriciels et Jeux Partiellement Observables", Paris, France, (2011)

  39. Minimizing regret with partial monitoring, Annual conference of the Research Group "Mathematics of Optimization and Application", Paris, France, (2010)

  40. Geometric properties of the best reply correspondence, Summer School in Game Theory, Aussois, France, (2010)

  41. Approachability in Wasserstein space, Seminar of calculous of variations, Paris, France, (2010)

  42. Games with Imperfect Monitoring: Calibrated approach, Seminar of Applied Analysis, Brest, France, (2009)

  43. Approachability with signals and no-regret procedures, Parisian Seminar of Game Theory, Paris, France, (2009)

  44. Procedures with Bounded Recall, Seminar for Ph.D. Students in Game Theory, Paris, France, (2009)

  45. No-Regret Procedures and Approachability, Seminar for Ph.D. Students in Game Theory, Paris, France, (2008)

Vulgarisation et Valorisation

  1. Machine Learning (et Data Science) en Action, séminaire de vulgarisation, ENS Cachan (2016)

  2. Applications of a Standard Tool of Game Theory: Blackwell’s Approachability, Horizons des Mathématiques, (2013)

  3. Théorie des jeux, stratégies et équilibres de Nash. Séminaire IPR, (2013)

  4. Introduction à la Calibration et aux bandits manchots à plusieurs bras, Aide au TIPE, Université Paris 7, (2011)

  5. Théorèmes de min-max jeux répétés et prédiction, Mathématiques en Mouvement (Quick intro to game theory), Paris, France, (2011)

Soutenances

  1. (HDR) Online Learning, Statistical Games and Game Theory, Paris, France, (2014)

  2. (Ph.D.) Approchabilité, Calibration et Regret dans les Jeux à Observations Partielles, Paris, France, (2010)