Wang Chi Cheung

11 papers · 2019–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (15) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (4) 🏃 Academic Marathon (6) 🐝 Cross-Pollinator (10) 💎 Century Club (11) 📈 Trend Setter

Conferences

ICML (6) AISTATS (3) NIPS (1) UAI (1)

Top co-authors

Vincent Tan (3) Zixin Zhong (3) David Simchi-Levi (2) Ruihao Zhu (2) Lixing Lyu (2) Zitian Li (2) Vincent Y. F. Tan (1) Le Yang (1)

Keywords

multi-armed bandit (4) best arm identification (3) cascading bandit (2) dynamic regret (2) regret minimization (1) resource allocation (1) sequential decision (1) online prediction (1) optimistic exploration (1) probability of error (1) thompson sampling (1) partial feedback (1) concentration inequality (1) multi-objective optimization (1) upper confidence bound (1) regret bound (1) online algorithm (1) adversarial corruption (1) non-stationary environment (1) knapsack problem (1)

Papers

Near Optimal Non-asymptotic Sample Complexity of 1-Identification ICML 2025

Best Arm Identification with Possibly Biased Offline Data UAI 2025

Best Arm Identification with Resource Constraints AISTATS 2024

Leveraging (Biased) Information: Multi-armed Bandits with Offline Data ICML 2024

Bandits with Knapsacks: Advice on Time-Varying Demands ICML 2023

Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions ICML 2021

Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting ICML 2020

Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism ICML 2020

Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives NIPS 2019

Learning to Optimize under Non-Stationarity AISTATS 2019

A Thompson Sampling Algorithm for Cascading Bandits AISTATS 2019