Patrick Rebeschini

6 papers University of Oxford

• Does Stochastic Gradient really succeed for bandits?
• Does Stochastic Gradient really succeed for bandits?
• Meta-Learning Objectives for Preference Optimization
• Non-stationary Bandit Convex Optimization: A Comprehensive Study
• On the necessity of adaptive regularisation: Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls
• Stochastic Shortest Path with Sparse Adversarial Costs