影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
86.04/100
前 0.8%
全站排名 #546
发表论文16 篇
平均评分
年均产出8.0 篇/年
Haipeng Luo
研究方向
learning in games · online learning · bandits · reinforcement learning · learning theory · boosting
21
Simultaneous Swap Regret Minimization via KL-Calibration
NeurIPS 2025Spotlight
一作17
Comparator-Adaptive $\Phi$-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games
NeurIPS 2025Spotlight
三作20
Improved Bounds for Swap Multicalibration and Swap Omniprediction
NeurIPS 2025Spotlight
一作17
From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications
NeurIPS 2025Poster
二作17
Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
NeurIPS 2025Poster
三作17
Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality
NeurIPS 2025Poster
15
Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
ICLR 2025Poster
15
Contextual Linear Bandits with Delay as Payoff
ICML 2025Poster
三作11
Optimal Multiclass U-Calibration Error and Beyond
NeurIPS 2024Poster
一作11
On Tractable $\Phi$-Equilibria in Non-Concave Games
NeurIPS 2024Poster
三作14
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
NeurIPS 2024Poster
36
On Local Equilibrium in Non-Concave Games
ICLR 2024Rejected
三作33
Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
ICLR 2024Rejected
12
No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
NeurIPS 2024Poster
三作15
Provably Efficient Interactive-Grounded Learning with Personalized Reward
NeurIPS 2024Poster
三作18
Contextual Multinomial Logit Bandits with General Value Functions
NeurIPS 2024Poster
二作