Yan Dai
11 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Cross-Pollinator (12) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (5) π Renaissance Researcher (6)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(17)
π
Grand Slam
π
Triple Crown
π
Century Club
(11)
π₯
Unstoppable
(5)
Conferences
ICML (4)
COLT (2)
ICLR (2)
NIPS (2)
AAAI (1)
Top co-authors
Keywords
regret bound
(3)
adversarial learning
(3)
multi-armed bandit
(2)
linear function approximation
(2)
online learning
(2)
online mirror descent
(2)
markov decision process
(1)
regret minimization
(1)
importance sampling
(1)
multi-agent learning
(1)
bandit feedback
(1)
adversarial setting
(1)
online algorithm
(1)
convergence rate
(1)
delayed feedback
(1)
linear mdp
(1)
markov game
(1)
gradient-based optimizer
(1)
adversarial bandit
(1)
stochastic environment
(1)
Papers
Non-Monetary Mechanism Design without Distributional Information: Using Scarce Audits Wisely (Extended Abstract)
COLT 2025
uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
ICLR 2025
Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
ICML 2024
Refined Sample Complexity for Markov Games with Independent Linear Function Approximation (Extended Abstract)
COLT 2024
Variance-Aware Sparse Linear Bandits
ICLR 2023
The Crucial Role of Normalization in Sharpness-Aware Minimization
NIPS 2023
Refined Regret for Adversarial MDPs with Linear Function Approximation
ICML 2023
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning
ICML 2023
Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
NIPS 2022
Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
ICML 2022
RSGNet: Relation based Skeleton Graph Network for Crowded Scenes Pose Estimation
AAAI 2021