Log In Sign Up

An Analysis of Stochastic Variance Reduced Gradient for Linear Inverse Problems

by   Bangti Jin, et al.

Stochastic variance reduced gradient (SVRG) is a popular variance reduction technique for stochastic gradient descent (SGD). We provide a first analysis of the method for solving a class of linear inverse problems in the lens of the classical regularization theory. We prove that for a suitable constant step size schedule, the method can achieve an optimal convergence rate in terms of the noise level (under suitable regularity condition) and the variance of the SVRG iterate error is smaller than that by SGD. These theoretical findings are corroborated by a set of numerical experiments.


page 1

page 2

page 3

page 4


On the Saturation Phenomenon of Stochastic Gradient Descent for Linear Inverse Problems

Stochastic gradient descent (SGD) is a promising method for solving larg...

On the Discrepancy Principle for Stochastic Gradient Descent

Stochastic gradient descent (SGD) is a promising numerical method for so...

On the Convergence of Stochastic Gradient Descent for Nonlinear Ill-Posed Problems

In this work, we analyze the regularizing property of the stochastic gra...

The Practicality of Stochastic Optimization in Imaging Inverse Problems

In this work we investigate the practicality of stochastic gradient desc...

Statistical Learning and Inverse Problems: An Stochastic Gradient Approach

Inverse problems are paramount in Science and Engineering. In this paper...

A Stochastic Variance Reduced Gradient using Barzilai-Borwein Techniques as Second Order Information

In this paper, we consider to improve the stochastic variance reduce gra...

Learning Co-Sparse Analysis Operators with Separable Structures

In the co-sparse analysis model a set of filters is applied to a signal ...