Can I read Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method on EtoBox?

Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method by Liang, Jiaming is a scholarly article available to read on EtoBox.

What is Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method about?

This paper proposes a stochastic proximal point method to solve a stochastic convex composite optimization problem. High probability results in stochastic optimization typically hinge on restrictive assumptions on the stochastic gradient noise, for example, sub-Gaussian distributions. Assuming only weak conditions such as bounded variance of the stochastic gradient, this paper establishes a low sample complexity to obtain a high probability guarantee on the convergence of the proposed method. Additionally, a notable aspect of this work is the development of a subroutine to solve the proximal subproblem, which also serves as a novel technique for variance reduction.

Author

Liang, Jiaming

Published

2024

Language

EN