Search Results for author: Shiliang Zuo

Found 7 papers, 1 papers with code

New Perspectives in Online Contract Design: Heterogeneous, Homogeneous, Non-myopic Agents and Team Production

no code implementations11 Mar 2024 Shiliang Zuo

I study three different settings when the principal contracts with a $\textit{single}$ agent each round: 1.

Contextual Bandits with Online Neural Regression

no code implementations12 Dec 2023 Rohan Deb, Yikun Ban, Shiliang Zuo, Jingrui He, Arindam Banerjee

Based on such a perturbed prediction, we show a ${\mathcal{O}}(\log T)$ regret for online regression with both squared loss and KL loss, and subsequently convert these respectively to $\tilde{\mathcal{O}}(\sqrt{KT})$ and $\tilde{\mathcal{O}}(\sqrt{KL^*} + K)$ regret for NeuCB, where $L^*$ is the loss of the best policy.

Multi-Armed Bandits regression

Corruption-Robust Lipschitz Contextual Search

no code implementations26 Jul 2023 Shiliang Zuo

In a total of $C$ rounds, the signal may be corrupted, though the value of $C$ is \emph{unknown} to the learner.

TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness

no code implementations NeurIPS 2021 Zhuolin Yang, Linyi Li, Xiaojun Xu, Shiliang Zuo, Qian Chen, Pan Zhou, Benjamin I. P. Rubinstein, Ce Zhang, Bo Li

To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.

TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness

1 code implementation NeurIPS 2021 Zhuolin Yang, Linyi Li, Xiaojun Xu, Shiliang Zuo, Qian Chen, Benjamin Rubinstein, Pan Zhou, Ce Zhang, Bo Li

To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.

Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses

no code implementations21 Aug 2020 Shiliang Zuo

I design attack strategies against UCB and Thompson Sampling that only spend $\widehat{O}(\sqrt{\log T})$ cost.

Adversarial Attack Thompson Sampling

Notes on Worst-case Inefficiency of Gradient Descent Even in R^2

no code implementations17 Aug 2020 Shiliang Zuo

In non-convex settings, it has been shown that gradient descent is able to escape saddle points asymptotically and converge to local minimizers [Lee et.

Cannot find the paper you are looking for? You can Submit a new open access paper.