323 citations · 1k across the 34 of their papers we have counts for
7 papers · 1 filter
Landscape Correspondence of Empirical and Population Risks in the Eigendecomposition Problem
Shuang Li, Gongguo Tang, Michael B. Wakin
Spectral methods include a family of algorithms related to the eigenvectors of certain data-generated matrices. In this work, we are interested in studying the geometric landscape…
The Global Geometry of Centralized and Distributed Low-rank Matrix Recovery without Regularization
Shuang Li, Qiuwei Li, Zhihui Zhu +2
Low-rank matrix recovery is a fundamental problem in signal processing and machine learning. A recent very popular approach to recovering a low-rank matrix X is to factorize it as…
The Landscape of Non-convex Empirical Risk with Degenerate Population Risk
Shuang Li, Gongguo Tang, Michael B. Wakin
The landscape of empirical risk has been widely studied in a series of machine learning problems, including low-rank matrix factorization, matrix sensing, matrix completion, and ph…
Provable Bregman-divergence based Methods for Nonconvex and Non-Lipschitz Problems
Qiuwei Li, Zhihui Zhu, Gongguo Tang +1
The (global) Lipschitz smoothness condition is crucial in establishing the convergence theory for most optimization methods. Unfortunately, most machine learning and signal process…
Global Optimality in Distributed Low-rank Matrix Factorization
Zhihui Zhu, Qiuwei Li, Xinshuo Yang +2
We study the convergence of a variant of distributed gradient descent (DGD) on a distributed low-rank matrix approximation problem wherein some optimization variables are used for…
Demixing Sines and Spikes: Robust Spectral Super-resolution in the Presence of Outliers
Carlos Fernandez-Granda, Gongguo Tang, Xiaodong Wang +1
We consider the problem of super-resolving the line spectrum of a multisinusoidal signal from a finite number of samples, some of which may be completely corrupted. Measurements of…