activity
20182021
most citedHessian Eigenspectra of More Realistic Nonlinear Models

6 citations · 6 across the 1 of their papers we have counts for

collaborators
Showing stat.MLShow all

7 papers · 1 filter

stat.ML20216 cited

Hessian Eigenspectra of More Realistic Nonlinear Models

Zhenyu Liao, Michael W. Mahoney

Given an optimization problem, the Hessian matrix and its eigenspectrum can be used in many ways, ranging from designing more efficient second-order algorithms to performing model…

stat.ML2020

Sparse Quantized Spectral Clustering

Zhenyu Liao, Romain Couillet, Michael W. Mahoney

Given a large data matrix, sparsifying, quantizing, and/or performing other entry-wise nonlinear operations can have numerous benefits, ranging from speeding up iterative algorithm…

stat.ML2020

Kernel regression in high dimensions: Refined analysis beyond double descent

Fanghui Liu, Zhenyu Liao, Johan A. K. Suykens

In this paper, we provide a precise characterization of generalization properties of high dimensional kernel ridge regression across the under- and over-parameterized regimes, depe…

stat.ML2019

Inner-product Kernels are Asymptotically Equivalent to Binary Discrete Kernels

Zhenyu Liao, Romain Couillet

This article investigates the eigenspectrum of the inner product-type kernel matrix under a bina…

stat.ML2019

High Dimensional Classification via Regularized and Unregularized Empirical Risk Minimization: Precise Error and Optimal Loss

Xiaoyi Mai, Zhenyu Liao

This article provides, through theoretical analysis, an in-depth understanding of the classification performance of the empirical risk minimization framework, in both ridge-regular…

stat.ML2018

The Dynamics of Learning: A Random Matrix Approach

Zhenyu Liao, Romain Couillet

Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why d…