The common-directions method for regularized empirical risk minimization

MaRDI QIDQ5381111zbMATH OpenFDO

Authors Po-Wei Wang, Ching-pei Lee, Chih-Jen Lin

Publication date 7 June 2019

Full work available at URL http://jmlr.csail.mit.edu/papers/v20/16-309.html

zbMATH Keywords

convergenceempirical risk minimizationoptimization

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Nonlinear programming (90C30)

Recommendations

• Limited-memory common-directions method for large-scale optimization: convergence, parallelization, and distributed optimization
• An accelerated randomized proximal coordinate gradient method and its application to regularized empirical risk minimization
• Second-order stochastic optimization for machine learning in linear time
• An optimal first order method based on optimal quadratic averaging
• Regularized Newton methods for minimizing functions with Hölder continuous hessians

Cites work

• A finite newton method for classification
• A modified finite Newton method for fast solution of large scale linear SVMs
• A survey of nonlinear conjugate gradient methods
• Analysis and design of optimization algorithms via integral quadratic constraints
• Bundle methods for regularized risk minimization
• Convex optimization: algorithms and complexity
• Function minimization by conjugate gradients
• Gradient methods for minimizing composite functions
• scientific article; zbMATH DE number 3850830 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• scientific article; zbMATH DE number 823069 (Why is no real title available?)
• scientific article; zbMATH DE number 5060482 (Why is no real title available?)
• Introductory lectures on convex optimization. A basic course.
• LIBLINEAR: a library for large linear classification
• Newton's Method for Large Bound-Constrained Optimization Problems
• On the limited memory BFGS method for large scale optimization
• Quasi-Newton Methods, Motivation and Theory
• Some methods of speeding up the convergence of iteration methods
• Trust region Newton method for logistic regression

Cited in

(3)

• Limited-memory common-directions method for large-scale optimization: convergence, parallelization, and distributed optimization
• Search direction correction with normalized gradient makes first-order methods faster
• Quasi-Newton method with subspace gradients

Describes a project that uses

Uses Software

• LIBLINEAR

This page was built for publication: The common-directions method for regularized empirical risk minimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5381111)