Richard Combes
11 papers · 2014–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (18) π§ Keyword Pioneer π Cross-Pollinator (15) π Interdisciplinary Bridge π Conference Polyglot (5)
π
Academic Marathon
(10)
π£
Hot Topic Early Bird
π
Century Club
(11)
π₯
Unstoppable
(5)
Conferences
NIPS (5)
ALT (2)
COLT (2)
AISTATS (1)
ICML (1)
Top co-authors
Keywords
regret bound
(6)
multi-armed bandit
(4)
stochastic bandit
(3)
regret lower bound
(2)
unimodal bandit
(2)
bayesian inference
(2)
thompson sampling
(2)
online optimization
(1)
posterior distribution
(1)
posterior sampling
(1)
ucb algorithm
(1)
worker reliability
(1)
adversarial setting
(1)
polynomial time
(1)
label aggregation
(1)
regret minimization
(1)
upper confidence bound
(1)
sequential decision
(1)
streaming algorithm
(1)
continuous action space
(1)
Papers
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
NIPS 2024
Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles
AISTATS 2023
Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information
COLT 2022
On the Suboptimality of Thompson Sampling in High Dimensions
NIPS 2021
Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time
ALT 2021
Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling
ALT 2020
Minimal Exploration in Structured Stochastic Bandits
NIPS 2017
A Minimax Optimal Algorithm for Crowdsourcing
NIPS 2017
Combinatorial Bandits Revisited
NIPS 2015
Lipschitz Bandits: Regret Lower Bound and Optimal Algorithms
COLT 2014
Unimodal Bandits: Regret Lower Bounds and Optimal Algorithms
ICML 2014