1 citations · 1 across the 10 of their papers we have counts for
3 papers · 1 filter
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…
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…
Optimal Design for Reward Modeling in RLHF
Antoine Scheid, Etienne Boursier, Alain Durmus +4
Reinforcement Learning from Human Feedback (RLHF) has become a popular approach to align language models (LMs) with human preferences. This method involves collecting a large datas…