2013 ConstrainedStochasticGradientDe

• (Mu et al., 2013) ⇒ Yang Mu, Wei Ding, Tianyi Zhou, and Dacheng Tao. (2013). “Constrained Stochastic Gradient Descent for Large-scale Least Squares Problem.” In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ISBN:978-1-4503-2174-7 doi:10.1145/2487575.2487635

Subject Headings:

Cited By

• http://scholar.google.com/scholar?q=%222013%22+Constrained+Stochastic+Gradient+Descent+for+Large-scale+Least+Squares+Problem
• http://dl.acm.org/citation.cfm?id=2487575.2487635&preflayout=flat#citedby

Quotes

Author Keywords

• Large-scale least squares; least squares methods; online learning; parameter learning; stochastic optimization; stochastic programming

Abstract

The least squares problem is one of the most important regression problems in statistics, machine learning and data mining. In this paper, we present the Constrained Stochastic Gradient Descent (CSGD) algorithm to solve the large-scale least squares problem. CSGD improves the Stochastic Gradient Descent (SGD) by imposing a provable constraint that the linear regression line passes through the mean point of all the data points. It results in the best regret bound $O (\ log{T}) $, and fastest convergence speed among all first order approaches. Empirical studies justify the effectiveness of CSGD by comparing it with SGD and other state-of-the-art approaches. An example is also given to show how to use CSGD to optimize SGD based least squares problems to achieve a better performance.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2013 ConstrainedStochasticGradientDe	Dacheng Tao Wei Ding Yang Mu Tianyi Zhou			Constrained Stochastic Gradient Descent for Large-scale Least Squares Problem				10.1145/2487575.2487635		2013