activity
20242026
collaborators

9 papers

cs.LG2026

Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective

Etienne Boursier, Claire Boyer

Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, meas…

cs.LG2026

Online Decision-Focused Learning

Aymeric Capitaine, Maxime Haddouche, Eric Moulines +3

Decision-focused learning (DFL) is an increasingly popular paradigm for training predictive models whose outputs are used in decision-making tasks. Instead of merely optimizing for…

stat.AP2026

Test-then-Punish: A Statistical Approach to Repeated Games

Aymeric Capitaine, Antoine Scheid, Etienne Boursier +2

We study discounted infinitely repeated games in which players agree on a cooperative mixed action profile but, at each step, observe only the realized pure actions. This form of i…

cs.GT2025

Online Decision-Making in Tree-Like Multi-Agent Games with Transfers

Antoine Scheid, Etienne Boursier, Alain Durmus +2

The widespread deployment of Machine Learning systems everywhere raises challenges, such as dealing with interactions or competition between multiple learners. In that goal, we stu…

cs.GT2025

Prediction-Aware Learning in Multi-Agent Systems

Aymeric Capitaine, Etienne Boursier, Eric Moulines +2

The framework of uncoupled online learning in multiplayer games has made significant progress in recent years. In particular, the development of time-varying games has considerably…

cs.GT2025

Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality

Antoine Scheid, Aymeric Capitaine, Etienne Boursier +3

In economic theory, the concept of externality refers to any indirect effect resulting from an interaction between players that affects the social welfare. Most of the models withi…