Jiatai Huang

4 papers · 2022–2025 · 2 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ICLR (2) ICML (2)

Top co-authors

Longbo Huang (4) Yan Dai (3) Ling Pan (1) Yiqin Tan (1) Pihe Hu (1) Yu Chen (1)

Research topics

Machine Learning (4) Optimization & Theory (4) Mathematics & Optimization (2) Learning Types (2) Optimization (2) Artificial Intelligence (1) Deep Learning (1) Reinforcement Learning (1) Application Areas (1) Core AI (1) Methods (1) Techniques (1)

Keywords

regret bound (3) adversarial learning (2) multi-armed bandit (2) adversarial bandit (2) online learning (2) adversarial setting (1) online mirror descent (1) online algorithm (1) delayed feedback (1) stochastic bandit (1) sparse training (1) stochastic environment (1) heavy-tailed bandit (1) feedback delay (1) topology evolution (1) heavy-tailed multi-armed bandit (1) model compression (1) best-of-both-worlds algorithm (1) stochastic optimization (1) deep reinforcement learning (1)

Papers

uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs ICLR 2025 Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning ICML 2023 RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch ICLR 2023 Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits ICML 2022