The week's events
MonMonday | TueTuesday | WedWednesday | ThuThursday | FriFriday | SatSaturday | SunSunday |
---|---|---|---|---|---|---|
February 24, 2020
|
February 25, 2020
|
February 26, 2020
|
February 27, 2020(1 event)
Strategic information transmission with receiver's type-dependent decision sets, by Stephan Sémirat (GAEL, Grenoble)Strategic information transmission with receiver's type-dependent decision sets, by Stephan Sémirat (GAEL, Grenoble) – Strategic information transmission with receiver's type-dependent decision sets. Abstract: We consider a sender-receiver game, in which the sender has finitely many types and the receiver makes decisions in a bounded real interval. We assume that utility functions are concave, single-peaked and supermodular. After the cheap talk phase, the receiver makes a decision, which must fulfill a constraint (e.g., a participation constraint) that depends on the sender's type. Hence a necessary equilibrium condition is that the receiver maximizes his expected utility subject to the constraints of all positive probability types. This necessary condition may not hold at the receiver's prior belief, so that a non-revealing equilibrium may fail to exist. We propose a constructive algorithm that always achieves a partitional perfect Bayesian equilibrium Bâtiment IMAG (442) |
February 28, 2020
|
February 29, 2020
|
March 1, 2020
|
- 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.
- April 30, 2024 @ Bâtiment IMAG (442) -- Seminar Rémi Castera
Correlation of Rankings in Matching Markets