Patrick Rebeschini
~Patrick_Rebeschini1
8
论文总数
4.0
年均投稿
平均评分
接收情况7/8
会议分布
NeurIPS
5
ICLR
3
发表论文 (8 篇)
20257 篇
5
Non-stationary Bandit Convex Optimization: A Comprehensive Study
NeurIPS 2025Poster
4
Meta-Learning Objectives for Preference Optimization
NeurIPS 2025Poster
4
On the necessity of adaptive regularisation: Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls
NeurIPS 2025Spotlight
4
Learning Loss Landscapes in Preference Optimization
ICLR 2025Rejected
3
Stochastic Shortest Path with Sparse Adversarial Costs
NeurIPS 2025Poster
3
Learning mirror maps in policy mirror descent
ICLR 2025Poster
4
Does Stochastic Gradient really succeed for bandits?
NeurIPS 2025Oral