ZHIMING HUANG — accepted AI-conference papers

2025

Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret

Bingshan Hu, ZHIMING HUANG, Tianyue H. Zhang, Mathias Lécuyer, Nidhi Hegde

ICML 2025poster

We address differentially private stochastic bandit problems by leveraging Thompson Sampling with Gaussian priors and Gaussian differential privacy (GDP). We propose DP-TS-UCB, a novel parametrized private algorithm that enables trading off privacy and regret. DP-TS-UCB satisfies $ \tilde{O} \l…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

A near-optimal high-probability swap-Regret upper bound for multi-agent bandits in unknown general-sum games

Zhiming Huang, Jianping Pan

UAI 2023poster

In this paper, we study a multi-agent bandit problem in an unknown general-sum game repeated for a number of rounds (i.e., learning in a black-box game with bandit feedback), where a set of agents have no information about the underlying game structure and cannot observe each other’s actions and rew…

Cited by 4 Source ↗PDF ↗Scholar ↗