Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Stochastic OptimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization
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 OptimizationStochastic Variance-Reduced Cubic Regularized Newton Method
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
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 PredictionReanalysis of Variance Reduced Temporal Difference Learning
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 LearningStochastic Variance-reduced Gradient Descent for Low-rank Matrix Recovery from Linear Measurements
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…