Gilles Stoltz
17 papers · 2008–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏃 Academic Marathon (17)
🐣
Hot Topic Early Bird
🌉
Interdisciplinary Bridge
🏆
Keyword Champion
🌱
Topic Pioneer
🗃️
Keyword Collector
(57)
📈
Trend Setter
💎
Century Club
(17)
🚀
Conference Pioneer
Conferences
NIPS (5)
COLT (4)
JMLR (4)
ALT (2)
AISTATS (1)
ICML (1)
Top co-authors
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