Chung-Wei Lee
17 papers · 2018–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Conference Polyglot (5) π Academic Marathon (7) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (14)
π
Cross-Pollinator
(14)
πΊοΈ
Taxonomy Completionist
(21)
π
Triple Crown
π€
Dynamic Duo
(15)
β‘
Prolific Year
(5)
π₯
Unstoppable
(8)
π
Century Club
(17)
ποΈ
Keyword Collector
(63)
Conferences
NIPS (8)
COLT (4)
ICLR (2)
ICML (2)
CVPR (1)
Top co-authors
Keywords
regret bound
(8)
online learning
(6)
game theory
(4)
nash equilibrium
(3)
contextual bandit
(3)
zero-sum game
(2)
extensive-form game
(2)
optimistic learning
(2)
optimistic gradient descent
(2)
dynamic regret
(2)
last-iterate convergence
(2)
multi-armed bandit
(2)
self-concordant barrier
(2)
counterfactual regret minimization
(1)
linear function approximation
(1)
pac learning
(1)
multi-agent learning
(1)
sample complexity
(1)
minimax regret
(1)
markov decision process
(1)
Papers
Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
ICLR 2025
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
NIPS 2024
Context-lumpable stochastic bandits
NIPS 2023
Regret Matching+: (In)Stability and Fast Convergence in Games
NIPS 2023
Uncoupled Learning Dynamics with $O(\log T)$ Swap Regret in Multiplayer Games
NIPS 2022
Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games
ICML 2022
Near-Optimal No-Regret Learning Dynamics for General Convex Games
NIPS 2022
Linear Last-iterate Convergence in Constrained Saddle-point Optimization
ICLR 2021
Last-iterate Convergence in Extensive-Form Games
NIPS 2021
Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
ICML 2021
Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games
COLT 2021
Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses
NIPS 2021
Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs
NIPS 2020
A Closer Look at Small-loss Bounds for Bandits with Graph Feedback
COLT 2020
A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal and Parameter-free
COLT 2019
Achieving Optimal Dynamic Regret for Non-stationary Bandits without Prior Information
COLT 2019
Multi-Label Zero-Shot Learning With Structured Knowledge Graphs
CVPR 2018