Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach

02/20/2018
by   Ming Yu, et al.
0

We study the problem of recovery of matrices that are simultaneously low rank and row and/or column sparse. Such matrices appear in recent applications in cognitive neuroscience, imaging, computer vision, macroeconomics, and genetics. We propose a GDT (Gradient Descent with hard Thresholding) algorithm to efficiently recover matrices with such structure, by minimizing a bi-convex function over a nonconvex set of constraints. We show linear convergence of the iterates obtained by GDT to a region within statistical error of an optimal solution. As an application of our method, we consider multi-task learning problems and show that the statistical error rate obtained by GDT is near optimal compared to minimax rate. Experiments demonstrate competitive performance and much faster running speed compared to existing methods, on both simulations and real data sets.

READ FULL TEXT
research
02/21/2017

A Nonconvex Free Lunch for Low-Rank plus Sparse Matrix Recovery

We study the problem of low-rank plus sparse matrix recovery. We propose...
research
03/09/2017

Recovery of Sparse and Low Rank Components of Matrices Using Iterative Method with Adaptive Thresholding

In this letter, we propose an algorithm for recovery of sparse and low r...
research
03/03/2021

Riemannian thresholding methods for row-sparse and low-rank matrix recovery

In this paper, we present modifications of the iterative hard thresholdi...
research
12/20/2018

Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames

Many applications of machine learning involve the analysis of large data...
research
06/26/2018

Main effects and interactions in mixed and incomplete data frames

A mixed data frame (MDF) is a table collecting categorical, numerical an...
research
10/13/2022

Sketching low-rank matrices with a shared column space by convex programming

In many practical applications including remote sensing, multi-task lear...
research
09/19/2014

Statistical Estimation: From Denoising to Sparse Regression and Hidden Cliques

These notes review six lectures given by Prof. Andrea Montanari on the t...

Please sign up or login with your details

Forgot password? Click here to reset