activity
20182022
most citedFast Global Convergence for Low-rank Matrix Recovery via Riemannian Gradient Descent with Random Initialization

12 citations · 12 across the 1 of their papers we have counts for

collaborators

6 papers

cs.DS2022

Near-Linear Time and Fixed-Parameter Tractable Algorithms for Tensor Decompositions

Arvind V. Mahankali, David P. Woodruff, Ziyu Zhang

We study low rank approximation of tensors, focusing on the tensor train and Tucker decompositions, as well as approximations with tree tensor networks and more general tensor netw…

math.OC2021

Asymptotic Escape of Spurious Critical Points on the Low-rank Matrix Manifold

Thomas Y. Hou, Zhenzhen Li, Ziyun Zhang

We show that on the manifold of fixed-rank and symmetric positive semi-definite matrices, the Riemannian gradient descent algorithm almost surely escapes some spurious critical poi…

stat.ML2020★ 12 cited

Fast Global Convergence for Low-rank Matrix Recovery via Riemannian Gradient Descent with Random Initialization

Thomas Y. Hou, Zhenzhen Li, Ziyun Zhang

In this paper, we propose a new global analysis framework for a class of low-rank matrix recovery problems on the Riemannian manifold. We analyze the global behavior for the Rieman…

math.NA2019

Exponential convergence of Sobolev gradient descent for a class of nonlinear eigenproblems

Ziyun Zhang

We propose to use the Łojasiewicz inequality as a general tool for analyzing the convergence rate of gradient descent on a Hilbert manifold, without resorting to the continuous gra…

math.OC2019

Analysis of Asymptotic Escape of Strict Saddle Sets in Manifold Optimization

Thomas Y. Hou, Zhenzhen Li, Ziyun Zhang

In this paper, we provide some analysis on the asymptotic escape of strict saddles in manifold optimization using the projected gradient descent (PGD) algorithm. One of our main co…

math.NA2018

A Fast Hierarchically Preconditioned Eigensolver Based On Multiresolution Matrix Decomposition

Thomas Y. Hou, De Huang, Ka Chun Lam +1

In this paper we propose a new iterative method to hierarchically compute a relatively large number of leftmost eigenpairs of a sparse symmetric positive matrix under the multireso…