Improved SVRG for finite sum structure optimization with application to binary classification

DOI10.3934/jimo.2019052zbMath1476.65104OpenAlexW2951175872WikidataQ127669340 ScholiaQ127669340MaRDI QIDQ2244210

Guangmei Shao, Xiao Zheng, Gaohang Yu, Wei Xue

Publication date: 12 November 2021

Published in: Journal of Industrial and Management Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/jimo.2019052

zbMATH Keywords

stochastic optimizationonline learningvariance reductionmachine leaningtwo-point stepsize

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Online algorithms; streaming algorithms (68W27)

Related Items (1)

An online conjugate gradient algorithm for large-scale data analysis in machine learning

Cites Work

• Gradient methods with adaptive step-sizes
• Introductory lectures on convex optimization. A basic course.
• A new adaptive Barzilai and Borwein method for unconstrained optimization
• Projected Barzilai-Borwein methods for large-scale box-constrained quadratic programming
• Multivariate spectral gradient projection method for nonlinear monotone equations with convex constraints
• Trace-penalty minimization for large-scale eigenspace computation
• Computing extreme eigenvalues of large scale Hankel tensors
• On the asymptotic behaviour of some new gradient methods
• Two-Point Step Size Gradient Methods
• Gradient-based method with active set strategy for $\ell _1$ optimization
• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
• Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learning
• On the Barzilai and Borwein choice of steplength for the gradient method
• Approximate Dynamic Programming
• A Stochastic Approximation Method

This page was built for publication: Improved SVRG for finite sum structure optimization with application to binary classification