DeepAI AI Chat
Log In Sign Up

Sparse Relaxed Regularized Regression: SR3

07/14/2018
by   Travis Askham, et al.
University of Washington
0

Regularized regression problems are ubiquitous in statistical modeling, signal processing, and machine learning. Sparse regression in particular has been instrumental in scientific model discovery, including compressed sensing applications, variable selection, and high-dimensional analysis. We propose a new and highly effective approach for regularized regression, called SR3. The key idea is to solve a relaxation of the regularized problem, which has three advantages over the state-of-the-art: (1) solutions of the relaxed problem are superior with respect to errors, false positives, and conditioning, (2) relaxation allows extremely fast algorithms for both convex and nonconvex formulations, and (3) the methods apply to composite regularizers such as total variation (TV) and its nonconvex variants. We demonstrate the improved performance of SR3 across a range of regularized regression problems with synthetic and real data, including compressed sensing, LASSO, matrix completion and TV regularization. To promote reproducible research, we include a companion Matlab package that implements these popular applications.

READ FULL TEXT

page 2

page 4

page 7

page 8

page 20

page 21

06/26/2020

Relaxed regularization for linear inverse problems

We consider regularized least-squares problems of the form min_x1/2‖ Ax ...
05/10/2019

Robust high dimensional learning for Lipschitz and convex losses

We establish risk bounds for Regularized Empirical Risk Minimizers (RERM...
06/05/2023

Compressed Sensing: A Discrete Optimization Approach

We study the Compressed Sensing (CS) problem, which is the problem of fi...
09/15/2015

Precise Phase Transition of Total Variation Minimization

Characterizing the phase transitions of convex optimizations in recoveri...
05/21/2019

Asymptotic Analysis for Extreme Eigenvalues of Principal Minors of Random Matrices

Consider a standard white Wishart matrix with parameters n and p. Motiva...
06/10/2022

Localized adversarial artifacts for compressed sensing MRI

As interest in deep neural networks (DNNs) for image reconstruction task...
07/17/2022

The Variable Projected Augmented Lagrangian Method

Inference by means of mathematical modeling from a collection of observa...