2018 GuaranteedSufficientDecreasefor

• (Shang et al., 2018) ⇒ Fanhua Shang, Yuanyuan Liu, Kaiwen Zhou, James Cheng, Kelvin Kai Wing Ng, and Yuichi Yoshida. (2018). “Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization.” In: Proceedings of Twenty-First International Conference on Artificial Intelligence and Statistics, PMLR (2018).

Subject Headings: Stochastic Variance Reduced Gradient Algorithm.

Cited By

• http://scholar.google.com/scholar?q=%222018%22+Guaranteed+Sufficient+Decrease+for+Stochastic+Variance+Reduced+Gradient+Optimization

Quotes

Abstract

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 a new sufficient decrease criterion, which yields sufficient decrease versions of stochastic variance reduction algorithms such as SVRG-SD and SAGA-SD as a byproduct. We introduce a coefficient to scale current iterate and to satisfy the sufficient decrease property, which takes the decisions to shrink, expand or even 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 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.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2018 GuaranteedSufficientDecreasefor	James Cheng Fanhua Shang Yuichi Yoshida Yuanyuan Liu Kaiwen Zhou Kelvin Kai Wing Ng			Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization