Stochastic sub-sampled Newton method with variance reduction

DOI10.1142/S0219691319500413zbMATH Open1433.62175OpenAlexW2945296329MaRDI QIDQ5204645FDOQ5204645

Authors: Zhijian Luo, Yun-Tao Qian 

Publication date: 5 December 2019

Published in: International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219691319500413

Recommendations

• Sub-sampled Newton methods
• Exact and inexact subsampled Newton methods for optimization
• Subsampled Hessian Newton Methods for Supervised Learning
• On the use of stochastic Hessian information in optimization methods for machine learning
• Nesterov's acceleration for approximate Newton

zbMATH Keywords

variance reductionlinear convergencelarge-scale stochastic optimizationsub-sampled Newton method

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Learning and adaptive systems in artificial intelligence (68T05) Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Image analysis in multivariate analysis (62H35)

Cites Work

• Adaptive subgradient methods for online learning and stochastic optimization
• A stochastic quasi-Newton method for large-scale optimization
• A Stochastic Approximation Method
• On the use of stochastic Hessian information in optimization methods for machine learning
• Incremental majorization-minimization optimization with application to large-scale machine learning
• Efficiency of coordinate descent methods on huge-scale optimization problems
• A proximal stochastic gradient method with progressive variance reduction
• Semi-stochastic coordinate descent
• Margin maximization in spherical separation
• Optimization Methods for Large-Scale Machine Learning
• Sketching as a tool for numerical linear algebra
• Title not available (Why is that?)
• Riemannian metrics for neural networks I: feedforward networks
• Title not available (Why is that?)

Cited In (2)

• On the use of stochastic Hessian information in optimization methods for machine learning
• Subsampled Hessian Newton Methods for Supervised Learning

Uses Software

• AdaGrad
• Finito
• Saga

This page was built for publication: Stochastic sub-sampled Newton method with variance reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5204645)