Xiao Zhang's Homepage
Xiao Zhang's Homepage
About
Research
Publication
Student
Teaching
Service
Contact
Open Position
Light
Dark
Automatic
1
Understanding Intrinsic Robustness using Label Uncertainty
Built upon on a novel definition of label uncertainty, we develop an empirical method to estimate a more realistic intirnsic robustness limit for image classification tasks.
Xiao Zhang
,
David Evans
PDF
Cite
ArXiv
OpenReview
Improved Estimation of Concentration Under Lp-Norm Distance Metric Using Half Spaces
We show that concentration of measure does not prohibit the existence of adversarially robust classifiers using a novel method of empirical concentration estimation.
Jack Prescott
,
Xiao Zhang
,
David Evans
PDF
Cite
Code
ArXiv
OpenReview
Post
Understanding the intrinsic robustness of image distributions using conditional generative models
We propose a way to characterize the intrinsic robustness of image distributions under L2 perturbations using conditional generative models.
Xiao Zhang
,
Jinghui Chen
,
Quanquan Gu
,
David Evans
PDF
Cite
Code
Slides
ArXiv
Link
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
We propose an unsupervised learning method for obtaining robust representations based on a notion of representation vulnerability.
Sicheng Zhu
,
Xiao Zhang
,
David Evans
PDF
Cite
Code
ArXiv
Link
Post
Empirically Measuring Concentration: Fundamental Limits to Intrinsic Robustness
We develop a method to measure the concentration of image benchmarks using empirical samples and show that concentration of measure does not prohibit the existence of adversarially robust classifiers.
Saeed Mahloujifar
,
Xiao Zhang
,
Mohammad Mahmoody
,
David Evans
PDF
Cite
Code
Poster
ArXiv
Post
Cost-Sensitive Robustness against Adversarial Examples
We propose a notion of cost-sensitive robustness for measuring classifier’s performance when adversarial transformations are not equally important, and provide a certified robust training method to optimize for it.
Xiao Zhang
,
David Evans
PDF
Cite
Code
Poster
ArXiv
OpenReview
Post
Learning One-hidden-layer ReLU Networks via Gradient Descent
We prove theoretical guarantees of learning one-hidden-layer neural networks with ReLU activations.
Xiao Zhang
,
Yaodong Yu
,
Lingxiao Wang
,
Quanquan Gu
PDF
Cite
Poster
ArXiv
Link
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery
A primal-dual based framework for analyzing the global optimality of nonconvex low-rank matrix recovery.
Xiao Zhang
,
Lingxiao Wang
,
Yaodong Yu
,
Quanquan Gu
PDF
Cite
Link
Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow
We present a new gradient-based optimization algorithm for inductive matrix completion, which achieves both linear rate of convengence and sample complexities linearly depending on the feature dimension.
Xiao Zhang
,
Simon Du
,
Quanquan Gu
PDF
Cite
Code
Poster
ArXiv
Link
A Unified Framework for Nonconvex Low-rank plus Sparse Matrix Recovery
A unified framework for solving general low-rank plus sparse matrix recovery problems.
Xiao Zhang
,
Lingxiao Wang
,
Quanquan Gu
PDF
Cite
Code
Poster
ArXiv
Link
»
Cite
×