Zhichao Wang

Postdoctoral Researcher Department of Statistics, University of California, Berkeley International Computer Science Institute Contact: zhichao (dot) wang (at) berkeley (dot) edu CV · Google Scholar· GitHub

About me

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

Research

My current research focuses on developing the mathematical and computational foundations of artificial intelligence using tools from high-dimensional probability and numerical linear algebra.

• Deep Learning Theory and Foundations of AI

• Randomized Numerical Linear Algebra and Optimization in LLM

• Random Matrix Theory

Selected Papers

• Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data.
  Collin Cranston, Zhichao Wang, Todd Kemp, W. Michael Mahoney
  39th Annual Conference on Learning Theory.

• Anisotropic local law for non-separable sample covariance matrices.
  Zhou Fan, Renyuan Ma, Elliot Paquette, Zhichao Wang
  Submitted.

• PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training.
  Shenghao Yang, Zhichao Wang, Oleg Balabanov, N Benjamin Erichson, Michael W Mahoney.
  ICML 2026.

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

• 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.

• 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.

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