Gilles Stoltz
17 papers · 2008–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🗺️ Taxonomy Completionist (24) 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Bronze 🏃 Academic Marathon · Full
🏆
Keyword Champion
📈
Trend Setter
🚀
Conference Pioneer
💎
Century Club · Bronze
🗃️
Keyword Collector
(63)
Top co-authors
Research topics
Keywords
regret bound
(11)
online learning
(8)
multi-armed bandit
(6)
stochastic optimization
(6)
regret minimization
(5)
contextual bandit
(3)
online optimization
(2)
kullback-leibler divergence
(2)
stochastic bandit
(2)
partial monitoring
(2)
game theory
(2)
online algorithm
(2)
adversarial learning
(2)
online linear regression
(1)
convex optimization
(1)
policy optimization
(1)
learning theory
(1)
minimax optimality
(1)
mirror descent
(1)
sample complexity
(1)
Papers
Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization
AISTATS 2025
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
Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness
NeurIPS 2023
Contextual Bandits with Knapsacks for a Conversion Model
NeurIPS 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
NeurIPS 2021
Target Tracking for Contextual Bandits: Application to Demand Side Management
ICML 2019
Uniform regret bounds over R^d for the sequential linear regression problem with the square loss
ALT 2019
Approachability in unknown games: Online learning meets multi-objective optimization
COLT 2014
A second-order bound with excess losses
COLT 2014
Set-Valued Approachability and Online Learning with Partial Monitoring
JMLR 2014
Mirror Descent Meets Fixed Share (and feels no regret)
NeurIPS 2012
A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences
COLT 2011
-Armed Bandits
JMLR 2011
Robust approachability and regret minimization in games with partial monitoring
COLT 2011
Online Optimization in X-Armed Bandits
NeurIPS 2008