← Authors

Gilles Stoltz

17 papers · 2008–2025 · 6 conferences · across top CS/AI conferences

Achievements

๐Ÿ Cross-Pollinator (12) ๐Ÿ—บ๏ธ Taxonomy Completionist (24) ๐ŸŒ Conference Polyglot (6) ๐Ÿƒ Academic Marathon (17) ๐Ÿงญ Keyword Pioneer ๐Ÿฃ Hot Topic Early Bird ๐ŸŒ‰ Interdisciplinary Bridge ๐Ÿ† Keyword Champion ๐ŸŒฑ Topic Pioneer ๐Ÿ—ƒ๏ธ Keyword Collector (57) ๐Ÿ“ˆ Trend Setter ๐Ÿ’Ž Century Club (17) ๐Ÿš€ Conference Pioneer

Conferences

NIPS (5) COLT (4) JMLR (4) ALT (2) AISTATS (1) ICML (1)

Top co-authors

Pierre Gaillard (4) Evgenii Chzhen (3) Shie Mannor (3) Rรฉmi Munos (3) Vianney Perchet (3) Csaba Szepesvรกri (2) Sรฉbastien Bubeck (2) Hedi Hadiji (2) Aurรฉlien Garivier (2) Zhen Li (2)

Keywords

regret bound (10) online learning (8) stochastic optimization (6) multi-armed bandit (6) regret minimization (5) contextual bandit (3) game theory (2) online optimization (2) kullback-leibler divergence (2) stochastic bandit (2) online algorithm (2) adversarial learning (2) partial monitoring (2) arm selection (1) linear programming (1) online linear regression (1) convex optimization (1) learning theory (1) projected gradient descent (1) weight sharing (1)

Papers

Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization AISTATS 2025
Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness NIPS 2023
Adaptation to the Range in K-Armed Bandits JMLR 2023
On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits ALT 2023
Contextual Bandits with Knapsacks for a Conversion Model NIPS 2022
KL-UCB-Switch: Optimal Regret Bounds for Stochastic Bandits from Both a Distribution-Dependent and a Distribution-Free Viewpoints JMLR 2022
A Unified Approach to Fair Online Learning via Blackwell Approachability NIPS 2021
Target Tracking for Contextual Bandits: Application to Demand Side Management ICML 2019
Uniform regret bounds over $\mathbb{R}^d$ for the sequential linear regression problem with the square loss ALT 2019
A second-order bound with excess losses COLT 2014
Approachability in unknown games: Online learning meets multi-objective optimization COLT 2014
Set-Valued Approachability and Online Learning with Partial Monitoring JMLR 2014
Mirror Descent Meets Fixed Share (and feels no regret) NIPS 2012
A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences COLT 2011
Robust approachability and regret minimization in games with partial monitoring COLT 2011
-Armed Bandits JMLR 2011
Online Optimization in X-Armed Bandits NIPS 2008