Faculty
Xiao Zhang is a tenure-track faculty at CISPA Helmholtz Center for Information Security. His research covers topics such as adversarial machine learning, statistical machine learning and optimization. He is particularly intersted in understanding the misbehavior of machine learning models against different adversaries and designing robust systems for various machine learning applications. He received his Ph.D. degree in computer science from University of Virginia, advised by Prof. David Evans in 2022. Prior to that, he obtained his M.S. degree from Department of Statistics at University of Virginia and obtained his B.S. degree in Mathematics from Tsinghua University. He is also a member of the European Laboratory for Learning and Intelligent Systems (ELLIS).
International Conference on Learning Representations (ICLR)
Improved Estimation of Concentration Under Lp-Norm Distance Metric Using Half Spaces
International Conference on Machine Learning (ICML)
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
International Conference on Artificial Intelligence and Statistics (AISTATS)
Understanding the intrinsic robustness of image distributions using conditional generative models
Conference on Neural Information Processing Systems (NeurIPS)
Empirically Measuring Concentration: Fundamental Limits to Intrinsic Robustness
International Conference on Learning Representations (ICLR)
Cost-Sensitive Robustness against Adversarial Examples
International Conference on Artificial Intelligence and Statistics (AISTATS)
Learning One-hidden-layer ReLU Networks via Gradient Descent
International Conference on Machine Learning (ICML)
Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow
International Conference on Machine Learning (ICML)
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery
International Conference on Artificial Intelligence and Statistics (AISTATS)
A Unified Framework for Low-Rank plus Sparse Matrix Recovery
International Conference on Machine Learning (ICML)
A Universal Variance Reduction-Based Catalyst for Nonconvex Low-Rank Matrix Recovery