ASPDC: Accelerated SPDC Regularized Empirical Risk Minimization for Ill-Conditioned Problems in Large-Scale Machine Learning

ASPDC: Accelerated SPDC Regularized Empirical Risk Minimization for Ill-Conditioned Problems in Large-Scale Machine Learning

This paper aims to improve the response speed of SPDC (stochastic primal–dual coordinate ascent) in large-scale machine learning, as the complexity of per-iteration of SPDC is not satisfactory. We propose an accelerated stochastic primal–dual coordinate ascent called ASPDC and its further accelerate...

Full description

Bibliographic Details
Main Authors: Haobang Liang, Hao Cai, Hejun Wu, Fanhua Shang, James Cheng, Xiying Li
Format: Article
Language:English
Published: MDPI AG 2022-07-01
Series:Electronics
Subjects:
stochastic optimization
machine learning
empirical risk minimization
coordinate ascent algorithm
primal–dual algorithm
strongly convex and smooth
Online Access:https://www.mdpi.com/2079-9292/11/15/2382

Similar Items

Similar Items