Yan Dai

11 papers · 2021–2025 · 5 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 ↓

🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏆 Grand Slam

👑 Triple Crown 🌈 Renaissance Researcher (5) 🔥 Unstoppable · Bronze 💎 Century Club · Bronze 🗃️ Keyword Collector (55)

Venues

ICML (4) COLT (2) ICLR (2) NeurIPS (2) AAAI (1)

Top co-authors

Jiatai Huang (3) Longbo Huang (3) Haipeng Luo (2) Kwangjun Ahn (2) Yunbum Kook (1) Julian Zimmert (1) Xuanhan Wang (1) Chen-Yu Wei (1) Suvrit Sra (1) Yu Chen (1)

Research topics

Machine Learning (9) Optimization & Theory (9) Mathematics & Optimization (4) Reinforcement Learning (4) Learning Types (4) Methods (4) Optimization (4) Artificial Intelligence (1) Computer Science (1) Computer Vision (1) Deep Learning (1) Analysis (1) Core AI (1) Foundations (1) Techniques (1)

Keywords

regret bound (4) online learning (3) adversarial learning (3) adversarial bandit (2) linear function approximation (2) multi-armed bandit (2) online mirror descent (2) human pose estimation (1) importance sampling (1) sample complexity (1) regret minimization (1) multi-agent learning (1) markov decision process (1) parameter-free algorithm (1) non-convex optimization (1) divide and conquer (1) neural network optimization (1) adversarial setting (1) minimax regret (1) bandit feedback (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 Refined Sample Complexity for Markov Games with Independent Linear Function Approximation (Extended Abstract) COLT 2024 Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise ICML 2024 Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning ICML 2023 Refined Regret for Adversarial MDPs with Linear Function Approximation ICML 2023 The Crucial Role of Normalization in Sharpness-Aware Minimization NeurIPS 2023 Variance-Aware Sparse Linear Bandits ICLR 2023 Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits ICML 2022 Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback NeurIPS 2022 RSGNet: Relation based Skeleton Graph Network for Crowded Scenes Pose Estimation AAAI 2021