Multi-Iteration Stochastic Optimizers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Carlon, Andre, Espath, Luis, Lopez, Rafael, Tempone, Raul
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917538916466688
author Carlon, Andre
Espath, Luis
Lopez, Rafael
Tempone, Raul
author_facet Carlon, Andre
Espath, Luis
Lopez, Rafael
Tempone, Raul
contents We introduce Multi-Iteration Stochastic Optimizers, a novel class of first-order stochastic methods that control the relative $L^2$ error using successive control variates along the iteration path. By exploiting correlations between iterates, these control variates reduce the estimator's variance, making an accurate mean gradient estimation computationally affordable. Our approach centers on the Multi-Iteration stochastiC Estimator (MICE), which can be seamlessly coupled with any first-order stochastic optimizer due to its non-intrusive design. The algorithm adaptively selects which iterates to include in its index set. We provide both an error analysis of MICE and a convergence analysis for Multi-Iteration Stochastic Optimizers across various problem classes, including some non-convex cases. In the smooth, strongly convex setting, we demonstrate that to approximate a minimizer within a tolerance $tol$, SGD-MICE requires, on average, $O(tol^{-1})$ stochastic gradient evaluations, compared to $O(tol^{-1}\log(tol^{-1}))$ for SGD with adaptive batch sizes. In numerical experiments, SGD-MICE achieved the desired tolerance with fewer than 3\% of the gradient evaluations required by adaptive batch SGD. Additionally, MICE offers a straightforward stopping criterion based on the gradient norm, validated through consistency tests. To assess its efficiency, we present examples using both SGD-MICE and Adam-MICE, including a stochastic adaptation of the Rosenbrock function and logistic regression on various datasets. Compared to SGD, SAG, SAGA, SVRG, and SARAH, our approach consistently reduces the gradient sampling cost without the need for extensive parameter tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2011_01718
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Multi-Iteration Stochastic Optimizers
Carlon, Andre
Espath, Luis
Lopez, Rafael
Tempone, Raul
Optimization and Control
62L20, 65K05, 90C15, 65C05
We introduce Multi-Iteration Stochastic Optimizers, a novel class of first-order stochastic methods that control the relative $L^2$ error using successive control variates along the iteration path. By exploiting correlations between iterates, these control variates reduce the estimator's variance, making an accurate mean gradient estimation computationally affordable. Our approach centers on the Multi-Iteration stochastiC Estimator (MICE), which can be seamlessly coupled with any first-order stochastic optimizer due to its non-intrusive design. The algorithm adaptively selects which iterates to include in its index set. We provide both an error analysis of MICE and a convergence analysis for Multi-Iteration Stochastic Optimizers across various problem classes, including some non-convex cases. In the smooth, strongly convex setting, we demonstrate that to approximate a minimizer within a tolerance $tol$, SGD-MICE requires, on average, $O(tol^{-1})$ stochastic gradient evaluations, compared to $O(tol^{-1}\log(tol^{-1}))$ for SGD with adaptive batch sizes. In numerical experiments, SGD-MICE achieved the desired tolerance with fewer than 3\% of the gradient evaluations required by adaptive batch SGD. Additionally, MICE offers a straightforward stopping criterion based on the gradient norm, validated through consistency tests. To assess its efficiency, we present examples using both SGD-MICE and Adam-MICE, including a stochastic adaptation of the Rosenbrock function and logistic regression on various datasets. Compared to SGD, SAG, SAGA, SVRG, and SARAH, our approach consistently reduces the gradient sampling cost without the need for extensive parameter tuning.
title Multi-Iteration Stochastic Optimizers
topic Optimization and Control
62L20, 65K05, 90C15, 65C05
url https://arxiv.org/abs/2011.01718