Zhichao Wang

Zhichao Wang Postdoctoral researcher at Department of Statistics International Computer Science Institute University of California, Berkeley Contact: zhichao.wang (at) berkeley (dot) edu Curriculum Vitae Google Scholar

About me

I am a postdoctoral researcher with a joint appointment in the Department of Statistics at University of California, Berkeley, and International Computer Science Institute, working with Michael Mahoney. I received my Ph.D. from the Department of Mathematics at University of California San Diego, where I was fortunate to be advised by Ioana Dumitriu and Todd Kemp.

Research Interests

My current research focuses on developing the mathematical foundations of artificial intelligence, especially in deep learning, using tools from high-dimensional probability.

• Deep Learning Theory and Foundations of AI

• Randomized Numerical Linear Algebra and Optimization in LLM

• Random Matrix Theory and Free Probability Theory

Publications and Preprints

• Singular values of sparse random rectangular matrices: Emergence of outliers at criticality.
  Ioana Dumitriu, Hai-Xiao Wang, Zhichao Wang, Yizhe Zhu
  Submitted

• Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel.
  Yilan Chen, Zhichao Wang, Wei Huang, Andi Han, Taiji Suzuki, Arya Mazumdar
  NeurIPS 2025.

• Models of Heavy-Tailed Mechanistic Universality.
  Liam Hodgkinson, Zhichao Wang, and Michael W. Mahoney
  ICML 2025.

• Universality of kernel random matrices and kernel regression in the quadratic regime.
  Parthe Pandit, Zhichao Wang, and Yizhe Zhu
  Journal of Machine Learning Research.

• Nonlinear spiked covariance matrices and signal propagation in deep neural networks.
  Zhichao Wang, Denny Wu, and Zhou Fan
  37th Annual Conference on Learning Theory.

• Unlocking Exact Recovery in Semi-Supervised Learning: Analysis of Spectral Method and Graph Convolution Network.
  Hai-Xiao Wang and Zhichao Wang
  ICML 2024.

• Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models.
  Andrew Engel, Zhichao Wang, Natalie S. Frank, Ioana Dumitriu, Sutanay Choudhury, Anand Sarwate, and Tony Chiang
  ICLR 2024, Spotlight.

• Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective.
  Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, and Denny Wu
  NeurIPS 2023.

• Spectral evolution and invariance in linear-width neural networks.
  Zhichao Wang, Andrew Engel, Anand Sarwate, Ioana Dumitriu, and Tony Chiang
  NeurIPS 2023.

• Overparameterized random feature regression with nearly orthogonal data.
  Zhichao Wang and Yizhe Zhu
  AISTATS 2023.

• High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation.
  Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki, Zhichao Wang, Denny Wu, and Greg Yang
  NeurIPS 2022.

• Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks.
  Zhichao Wang and Yizhe Zhu
  Annals of Applied Probability.

• Tree convolution for probability distributions with unbounded support.
  Ethan Davis, David Jekel, Zhichao Wang
  Latin American Journal of Probability and Mathematics Statistics 18.2 (2021), pp. 1585-1623.

• Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks.
  Zhou Fan and Zhichao Wang
  NeurIPS 2020, Oral Presentation.

• Principal components in linear mixed models with general bulk.
  Zhou Fan, Yi Sun, and Zhichao Wang
  The Annals of Statistics, 49.3 (2021), pp. 1489-1513.

• Higher variations for free Levy processes.
  Michael Anshelevich and Zhichao Wang
  Studia Math. 252 (2020), pp. 49-81.