Patrick Rebeschini

Full Professor@University of Oxford·英国·OpenReview

研究方向

Statistical learning theory · optimization · online learning · reinforcement learning · Distributed systems · sensor networks · message passing · Signal processing · Monte Carlo · particle filters

4.7

Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis

ICLR 2026Poster

二作

8.7

On the necessity of adaptive regularisation: Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls

NeurIPS 2025Spotlight

合作者 (18)

Jakob Nicolaus Foerster

Patrick Rebeschini

Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis

On the necessity of adaptive regularisation: Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls

Does Stochastic Gradient really succeed for bandits?

Non-stationary Bandit Convex Optimization: A Comprehensive Study

Meta-Learning Objectives for Preference Optimization

Learning mirror maps in policy mirror descent

Stochastic Shortest Path with Sparse Adversarial Costs

Learning Loss Landscapes in Preference Optimization