TY  - JOUR
UR  - https://doi.org/10.1088/1361-6420/ac4428
PB  - IOP Publishing
ID  - discovery10140922
N2  - Stochastic variance reduced gradient (SVRG) is a popular variance reduction technique for accelerating 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.
A1  - Jin, B
A1  - Zhou, Z
A1  - Zou, J
JF  - Inverse Problems
Y1  - 2021/01/04/
AV  - public
VL  - 38
TI  - An analysis of stochastic variance reduced gradient for linear inverse problems
N1  - This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
IS  - 2
ER  -