English
Related papers

Related papers: SVRG for Policy Evaluation with Fewer Gradient Eva…

200 papers

We study optimization algorithms based on variance reduction for stochastic gradient descent (SGD). Remarkable recent progress has been made in this direction through development of algorithms like SAG, SVRG, SAGA. These algorithms have…

Machine Learning · Computer Science 2016-01-26 Sashank J. Reddi , Ahmed Hefny , Suvrit Sra , Barnabás Póczos , Alex Smola

In this paper, we revisit and improve the convergence of policy gradient (PG), natural PG (NPG) methods, and their variance-reduced variants, under general smooth policy parametrizations. More specifically, with the Fisher information…

Machine Learning · Computer Science 2022-11-17 Yanli Liu , Kaiqing Zhang , Tamer Başar , Wotao Yin

We propose two policy gradient algorithms for solving the problem of control in an off-policy reinforcement learning (RL) context. Both algorithms incorporate a smoothed functional (SF) based gradient estimation scheme. The first algorithm…

Machine Learning · Computer Science 2024-06-25 Nithia Vijayan , Prashanth L. A

In this paper, we propose a StochAstic Recursive grAdient algoritHm (SARAH), as well as its practical variant SARAH+, as a novel approach to the finite-sum minimization problems. Different from the vanilla SGD and other modern stochastic…

Machine Learning · Statistics 2017-09-08 Lam M. Nguyen , Jie Liu , Katya Scheinberg , Martin Takáč

Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness,…

Machine Learning · Computer Science 2016-02-29 Thomas Hofmann , Aurelien Lucchi , Simon Lacoste-Julien , Brian McWilliams

In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. More precisely, we interpret a large class of…

Machine Learning · Statistics 2020-09-07 Andrei Kulunchakov , Julien Mairal

We investigate the problem of learning an $\epsilon$-approximate solution for the discrete-time Linear Quadratic Regulator (LQR) problem via a Stochastic Variance-Reduced Policy Gradient (SVRPG) approach. Whilst policy gradient methods have…

Optimization and Control · Mathematics 2023-09-20 Leonardo F. Toso , Han Wang , James Anderson

Estimating a policy that maps states to actions is a central problem in reinforcement learning. Traditionally, policies are inferred from the so called value functions (VFs), but exact VF computation suffers from the curse of…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques

Variance reduction techniques like SVRG provide simple and fast algorithms for optimizing a convex finite-sum objective. For nonconvex objectives, these techniques can also find a first-order stationary point (with small gradient). However,…

Machine Learning · Computer Science 2019-05-03 Rong Ge , Zhize Li , Weiyao Wang , Xiang Wang

Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions. Unfortunately, these techniques are unable to deal with stochastic perturbations of input data, induced for…

Machine Learning · Statistics 2017-11-16 Alberto Bietti , Julien Mairal

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…

Machine Learning · Computer Science 2017-06-06 Fanhua Shang , Yuanyuan Liu , James Cheng , Kelvin Kai Wing Ng , Yuichi Yoshida

A new amortized variance-reduced gradient (AVRG) algorithm was developed in \cite{ying2017convergence}, which has constant storage requirement in comparison to SAGA and balanced gradient computations in comparison to SVRG. One key advantage…

Machine Learning · Computer Science 2018-05-30 Kun Yuan , Bicheng Ying , Jiageng Liu , Ali H. Sayed

In this paper, we propose a vector transport-free stochastic variance reduced gradient (SVRG) method with general retraction for empirical risk minimization over Riemannian manifold. Existing SVRG methods on manifold usually consider a…

Optimization and Control · Mathematics 2017-05-26 Bo Jiang , Shiqian Ma , Anthony Man-Cho So , Shuzhong Zhang

We propose the stochastic average gradient (SAG) method for optimizing the sum of a finite number of smooth convex functions. Like stochastic gradient (SG) methods, the SAG method's iteration cost is independent of the number of terms in…

Optimization and Control · Mathematics 2016-05-12 Mark Schmidt , Nicolas Le Roux , Francis Bach

Despite the rise to fame of incremental variance-reduced methods in recent years, their use in nonsmooth optimization is still limited to few simple cases. This is due to the fact that existing methods require to evaluate the proximity…

Optimization and Control · Mathematics 2019-01-28 Fabian Pedregosa , Kilian Fatras , Mattia Casotto

Variance-reduced stochastic gradient methods have gained popularity in recent times. Several variants exist with different strategies for the storing and sampling of gradients and this work concerns the interactions between these two…

Optimization and Control · Mathematics 2022-10-19 Martin Morin , Pontus Giselsson

In reinforcement learning (RL), offline learning decoupled learning from data collection and is useful in dealing with exploration-exploitation tradeoff and enables data reuse in many applications. In this work, we study two offline…

Machine Learning · Computer Science 2022-02-08 Jing Dong , Xin T. Tong

In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. This point of view covers the stochastic gradient…

Machine Learning · Statistics 2019-05-08 Andrei Kulunchakov , Julien Mairal

Our goal is to improve variance reducing stochastic methods through better control variates. We first propose a modification of SVRG which uses the Hessian to track gradients over time, rather than to recondition, increasing the correlation…

Optimization and Control · Mathematics 2018-04-03 Robert M. Gower , Nicolas Le Roux , Francis Bach

We analyse an iterative algorithm to minimize quadratic functions whose Hessian matrix $H$ is the expectation of a random symmetric $d\times d$ matrix. The algorithm is a variant of the stochastic variance reduced gradient (SVRG). In…

Machine Learning · Computer Science 2021-06-16 Nabil Kahale