Bingshan Hu

5 papers · 2019–2025 · 3 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 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (15) 🚀 Conference Pioneer

Venues

UAI (3) COLT (1) ICML (1)

Top co-authors

Nidhi Hegde (3) Tianyue H. Zhang (2) Nishant A. Mehta (2) Jianping Pan (1) Zhiming Huang (1) Mark Schmidt (1) Mathias Lécuyer (1)

Research topics

Machine Learning (5) Optimization & Theory (4) Mathematics & Optimization (3) Artificial Intelligence (2) Reinforcement Learning (2) Application Areas (2) Core AI (2) Learning Types (2) Optimization (2) Applications (1) Mathematics (1) Methods (1)

Keywords

thompson sampling (4) regret bound (4) stochastic bandit (3) differential privacy (2) multi-armed bandit (2) model-based reinforcement learning (1) gaussian priors (1) ucb algorithm (1) optimistic exploration (1) bayesian inference (1) gap-dependent rate (1) upper confidence bound (1) online learning (1) stochastic optimization (1) episodic reinforcement learning (1) feedback graph (1) stochastic online learning (1) anti-concentration bound (1) differentially private (1) markov decision process (1)

Papers

Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret ICML 2025 Open Problem: Optimal Rates for Stochastic Decision-Theoretic Online Learning Under Differentially Privacy COLT 2024 Optimistic Thompson Sampling-based algorithms for episodic reinforcement learning UAI 2023 Near-optimal Thompson sampling-based algorithms for differentially private stochastic bandits UAI 2022 Problem-dependent Regret Bounds for Online Learning with Feedback Graphs UAI 2019