SEMINARS

Events in April–May 2024

Monday Tuesday Wednesday Thursday Friday Saturday Sunday

April

April 1, 2024
April 2, 2024
April 3, 2024(1 event)

[Seminar] Victor Boone


April 3, 2024

Who: Victor Boone

When: Wednesday, April 3, 14:00-15:00

Where: 447

What: Learning MDPs with Extended Bellman Operators

More: Efficiently learning Markov Decision Processes (MDPs) is difficult. When facing an unknown environment, where is the adequate limit between repeating actions that have shown their efficiency in the past (exploitation of your knowledge) and testing alternatives that may actually be better than what you currently believe (exploration of the environment)? To bypass this dilemma, a well-known solution is the "optimism-in-face-of-uncertainty" principle: Think of the score of an action as being the largest that is statistically plausible.

The exploration-exploitation dilemma then becomes the problem of tuning optimism. In this talk, I will explain how optimism in MDPs can be all rephrased using a single operator, embedding all the uncertainty in your environment within a single MDP. This is a story about "extended Bellman operators" and "extended MDPs", and about how one can achieve minimax optimal regret using this machinery.

Bâtiment IMAG (442)
Saint-Martin-d'Hères, 38400
France
April 4, 2024
April 5, 2024
April 6, 2024
April 7, 2024
April 8, 2024
April 9, 2024
April 10, 2024
April 11, 2024(1 event)

[Seminar] Charles Arnal


April 11, 2024

Who: Charles Arnal

When: Thursday, April 11, 14:00-15:00

Where: 442

What: Mode Estimation with Partial Feedback

More: The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments. These new learning pipelines call for new theoretical frameworks. In this paper, we formalize core aspects of weakly supervised and active learning with a simple problem: the estimation of the mode of a distribution using partial feedback. We show how entropy coding allows for optimal information acquisition from partial feedback, develop coarse sufficient statistics for mode identification, and adapt bandit algorithms to our new setting. Finally, we combine those contributions into a statistically and computationally efficient solution to our problem.

Bâtiment IMAG (442)
Saint-Martin-d'Hères, 38400
France
April 12, 2024
April 13, 2024
April 14, 2024
April 15, 2024
April 16, 2024
April 17, 2024
April 18, 2024
April 19, 2024
April 20, 2024
April 21, 2024
April 22, 2024
April 23, 2024
April 24, 2024
April 25, 2024
April 26, 2024
April 27, 2024
April 28, 2024
April 29, 2024
April 30, 2024

May

May 1, 2024
May 2, 2024
May 3, 2024
May 4, 2024
May 5, 2024
May 6, 2024
May 7, 2024
May 8, 2024
May 9, 2024
May 10, 2024
May 11, 2024
May 12, 2024
May 13, 2024
May 14, 2024
May 15, 2024
May 16, 2024
May 17, 2024
May 18, 2024
May 19, 2024
May 20, 2024
May 21, 2024
May 22, 2024
May 23, 2024
May 24, 2024
May 25, 2024
May 26, 2024
May 27, 2024
May 28, 2024
May 29, 2024
May 30, 2024
May 31, 2024

June

June 1, 2024
June 2, 2024
  • March 26, 2024 @ Bâtiment IMAG (442) -- [Seminar] Romain Cravic

    Who: Romain Cravic

    When: Tuesday, March 26, 14:00-15:00

    Where: IMAG 406

    What: Résoudre les jeux partiellement observables : Algorithme CFR et variantes de Monte-Carlo, deuxième partie

    More: Dans ce séminaire en deux parties, je vous présenterai la famille des algorithmes CFR (CounterFactual Regret minimization) appliqués aux jeux sous forme extensive à information incomplète. CFR a été utilisé en 2015 par des chercheurs de l’université d’Alberta pour résoudre une version « réaliste » du poker (Heads-up limit poker). Dans la première partie nous verrons comment modéliser l’information incomplète pour les jeux à deux joueurs à somme nulle, comment définir des stratégies dans ce modèle, avant d’analyser en détail l’algorithme CFR qui calcule un approximation de l’équilibre de Nash du jeu. Pour aller plus loin, dans la seconde partie, nous étudierons les variantes dites « Monte-Carlo » de l’algorithme CFR qui sont indispensables quand on souhaite trouver des bonnes stratégies dans des jeux plus ambitieux.

  • April 3, 2024 @ Bâtiment IMAG (442) -- [Seminar] Victor Boone

    Who: Victor Boone

    When: Wednesday, April 3, 14:00-15:00

    Where: 447

    What: Learning MDPs with Extended Bellman Operators

    More: Efficiently learning Markov Decision Processes (MDPs) is difficult. When facing an unknown environment, where is the adequate limit between repeating actions that have shown their efficiency in the past (exploitation of your knowledge) and testing alternatives that may actually be better than what you currently believe (exploration of the environment)? To bypass this dilemma, a well-known solution is the "optimism-in-face-of-uncertainty" principle: Think of the score of an action as being the largest that is statistically plausible.

    The exploration-exploitation dilemma then becomes the problem of tuning optimism. In this talk, I will explain how optimism in MDPs can be all rephrased using a single operator, embedding all the uncertainty in your environment within a single MDP. This is a story about "extended Bellman operators" and "extended MDPs", and about how one can achieve minimax optimal regret using this machinery.

  • April 11, 2024 @ Bâtiment IMAG (442) -- [Seminar] Charles Arnal

    Who: Charles Arnal

    When: Thursday, April 11, 14:00-15:00

    Where: 442

    What: Mode Estimation with Partial Feedback

    More: The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments. These new learning pipelines call for new theoretical frameworks. In this paper, we formalize core aspects of weakly supervised and active learning with a simple problem: the estimation of the mode of a distribution using partial feedback. We show how entropy coding allows for optimal information acquisition from partial feedback, develop coarse sufficient statistics for mode identification, and adapt bandit algorithms to our new setting. Finally, we combine those contributions into a statistically and computationally efficient solution to our problem.

Comments are closed.