paper-with-me

Papers

Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent

2017-03-20 · Fanhua Shang, Yuanyuan Liu, James Cheng, Kelvin Kai Wing Ng, Yuichi Yoshida

In this paper, we propose a novel sufficient decrease technique for variance reduced stochastic gradient descent methods such as SAG, SVRG and SAGA. In order to make sufficient decrease for stochastic optimization, we design a new sufficient decrease criterion, which yields sufficient decrease versions of variance reduction algorithms such as SVRG-SD and SAGA-SD as a byproduct. We introduce a coefficient to scale current iterate and satisfy the sufficient decrease property, which takes the decisions to shrink, expand or move in the opposite direction, and then give two specific update rules of the coefficient for Lasso and ridge regression. Moreover, we analyze the convergence properties of our algorithms for strongly convex problems, which show that both of our algorithms attain linear convergence rates. We also provide the convergence guarantees of our algorithms for non-strongly convex problems. Our experimental results further verify that our algorithms achieve significantly better performance than their counterparts.

📄 PDF Abstract BibTeX arXiv:1703.06807

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Methods 이 논문이 사용한 방법론

SAGA SAGA is a method in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the…

Similar Papers 제목 키워드 기반

Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization

2018-02-26 · Fanhua Shang, Yuanyuan Liu, Kaiwen Zhou, James Cheng 외

In this paper, we propose a novel sufficient decrease technique for stochastic variance reduced gradient descent methods such as SVRG and SAGA. In order to make sufficient decrease for stochastic optimization, we design …

Stochastic Optimization

Stochastic Variance-Reduced Cubic Regularized Newton Method

2018-02-13 · ICML 2018 7 · Dongruo Zhou, Pan Xu, Quanquan Gu

We propose a stochastic variance-reduced cubic regularized Newton method for non-convex optimization. At the core of our algorithm is a novel semi-stochastic gradient along with a semi-stochastic Hessian, which are speci…

High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm

2017-08-01 · ICML 2017 8 · Rongda Zhu, Lingxiao Wang, ChengXiang Zhai, Quanquan Gu

We propose a generic stochastic expectation-maximization (EM) algorithm for the estimation of high-dimensional latent variable models. At the core of our algorithm is a novel semi-stochastic variance-reduced gradien…

parameter estimationVocal Bursts Intensity Prediction

Reanalysis of Variance Reduced Temporal Difference Learning

2020-01-07 · ICLR 2020 1 · Tengyu Xu, Zhe Wang, Yi Zhou, Yingbin Liang

Temporal difference (TD) learning is a popular algorithm for policy evaluation in reinforcement learning, but the vanilla TD can substantially suffer from the inherent optimization variance. A variance reduced TD (VRTD) …

Reinforcement Learning

Stochastic Variance-reduced Gradient Descent for Low-rank Matrix Recovery from Linear Measurements

2017-01-02 · Xiao Zhang, Lingxiao Wang, Quanquan Gu

We study the problem of estimating low-rank matrices from linear measurements (a.k.a., matrix sensing) through nonconvex optimization. We propose an efficient stochastic variance reduced gradient descent algorithm to sol…