Leverage score sampling for faster accelerated regression and ERM

MaRDI QIDQ7025156zbMATH OpenFDO

Authors Naman Agarwal, Sham M. Kakade, Rahul Kidambi, Yin Tat Lee, Praneeth Netrapalli, Aaron Sidford

Publication date 19 February 2025

Full work available at URL https://proceedings.mlr.press/v117/agarwal20a.html

zbMATH Keywords

convex optimizationempirical risk minimizationrandomized algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Randomized algorithms (68W20) Convex programming (90C25)

Cites work

• Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
• Efficiency of the accelerated coordinate descent method on structured optimization problems
• scientific article; zbMATH DE number 5485569 (Why is no real title available?)
• Iterative row sampling
• Low rank approximation and regression in input sparsity time
• Multiplying matrices faster than coppersmith-winograd
• Nearly tight oblivious subspace embeddings by trace inequalities
• OSNAP: faster numerical linear algebra algorithms via sparser subspace embeddings
• Uniform sampling for matrix approximation

This page was built for publication: Leverage score sampling for faster accelerated regression and ERM

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025156)