paper-with-me

홈 › Papers

Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning

2017-03-23 · Fanhua Shang, Yuanyuan Liu, James Cheng, Jiacheng Zhuo

Recently, research on accelerated stochastic gradient descent methods (e.g., SVRG) has made exciting progress (e.g., linear convergence for strongly convex problems). However, the best-known methods (e.g., Katyusha) requires at least two auxiliary variables and two momentum parameters. In this paper, we propose a fast stochastic variance reduction gradient (FSVRG) method, in which we design a novel update rule with the Nesterov's momentum and incorporate the technique of growing epoch size. FSVRG has only one auxiliary variable and one momentum weight, and thus it is much simpler and has much lower per-iteration complexity. We prove that FSVRG achieves linear convergence for strongly convex problems and the optimal $\mathcal{O}(1/T^2)$ convergence rate for non-strongly convex problems, where $T$ is the number of outer-iterations. We also extend FSVRG to directly solve the problems with non-smooth component functions, such as SVM. Finally, we empirically study the performance of FSVRG for solving various machine learning problems such as logistic regression, ridge regression, Lasso and SVM. Our results show that FSVRG outperforms the state-of-the-art stochastic methods, including Katyusha.

📄 PDF Abstract BibTeX arXiv:1703.07948

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learningregression

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Similar Papers 제목 키워드 기반

Momentum as Variance-Reduced Stochastic Gradient

2021-09-29 · Zih-Syuan Huang, Ching-pei Lee

Stochastic gradient descent with momentum (SGD+M) is widely used to empirically improve the convergence behavior and the generalization performance of plain stochastic gradient descent (SGD) in the training of deep learn…

Data Augmentation

Stochastic Recursive Momentum for Policy Gradient Methods

2020-03-09 · Huizhuo Yuan, Xiangru Lian, Ji Liu, Yuren Zhou

In this paper, we propose a novel algorithm named STOchastic Recursive Momentum for Policy Gradient (STORM-PG), which operates a SARAH-type stochastic recursive variance-reduced policy gradient in an exponential moving a…

Policy Gradient Methods

Momentum-Based Policy Gradient with Second-Order Information

2022-05-17 · Saber Salehkaleybar, Sadegh Khorasani, Negar Kiyavash, Niao He 외

Variance-reduced gradient estimators for policy gradient methods have been one of the main focus of research in the reinforcement learning in recent years as they allow acceleration of the estimation process. We propose …

Policy Gradient Methods

Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization

2019-02-07 · Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang 외

Two new stochastic variance-reduced algorithms named SARAH and SPIDER have been recently proposed, and SPIDER has been shown to achieve a near-optimal gradient oracle complexity for nonconvex optimization. However, the t…

Momentum-Based Policy Gradient Methods

2020-07-13 · ICML 2020 1 · Feihu Huang, Shangqian Gao, Jian Pei, Heng Huang

In the paper, we propose a class of efficient momentum-based policy gradient methods for the model-free reinforcement learning, which use adaptive learning rates and do not require any large batches. Specifically, we pro…

Policy Gradient Methods