Mengxiao Zhang

is this you? claim profile

0 followers
University of Southern California

Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously

In this work, we develop linear bandit algorithms that automatically ada...
02/11/2021 ∙ by Chung-Wei Lee, et al. ∙ 0 ∙ share

read it
Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games

We study infinite-horizon discounted two-player zero-sum Markov games, a...
02/08/2021 ∙ by Chen-Yu Wei, et al. ∙ 0 ∙ share

read it
The Relevance of Classic Fuzz Testing: Have We Solved This One?

As fuzz testing has passed its 30th anniversary, and in the face of the ...
08/14/2020 ∙ by Barton P. Miller, et al. ∙ 0 ∙ share

read it
RANDOM MASK: Towards Robust Convolutional Neural Networks

Robustness of neural networks has recently been highlighted by the adver...
07/27/2020 ∙ by Tiange Luo, et al. ∙ 19 ∙ share

read it
Linear Last-iterate Convergence for Matrix Games and Stochastic Games

Optimistic Gradient Descent Ascent (OGDA) algorithm for saddle-point opt...
06/16/2020 ∙ by Chung-Wei Lee, et al. ∙ 0 ∙ share

read it
Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs

We develop a new approach to obtaining high probability regret bounds fo...
06/14/2020 ∙ by Chung-Wei Lee, et al. ∙ 0 ∙ share

read it
Selling Data at an Auction under Privacy Constraints

Private data query combines mechanism design with privacy protection to ...
05/19/2020 ∙ by Mengxiao Zhang, et al. ∙ 0 ∙ share

read it
A Closer Look at Small-loss Bounds for Bandits with Graph Feedback

We study small-loss bounds for the adversarial multi-armed bandits probl...
02/02/2020 ∙ by Chung-Wei Lee, et al. ∙ 0 ∙ share

read it
Defective Convolutional Layers Learn Robust CNNs

Robustness of convolutional neural networks has recently been highlighte...
11/19/2019 ∙ by Tiange Luo, et al. ∙ 19 ∙ share

read it
The Local Dimension of Deep Manifold

Based on our observation that there exists a dramatic drop for the singu...
11/05/2017 ∙ by Mengxiao Zhang, et al. ∙ 0 ∙ share

read it

Mengxiao Zhang

Featured Co-authors

Liwei Wang

Di He

Kun He

Tao Yu

Haipeng Luo

Chen-Yu Wei

Siyu Chen

John E. Hopcroft

Tianle Cai

Chung-Wei Lee

Xiaojin Zhang

Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously

Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games

The Relevance of Classic Fuzz Testing: Have We Solved This One?

RANDOM MASK: Towards Robust Convolutional Neural Networks

Linear Last-iterate Convergence for Matrix Games and Stochastic Games

Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs

Selling Data at an Auction under Privacy Constraints

A Closer Look at Small-loss Bounds for Bandits with Graph Feedback

Defective Convolutional Layers Learn Robust CNNs

The Local Dimension of Deep Manifold