High-dimensional limit of one-pass SGD on least squares

DOI10.1214/23-ECP571zbMATH Open1544.60072MaRDI QIDQ6597217

Elliot Paquette, Elizabeth Collins-Woodfin

Publication date: 3 September 2024

Published in: Electronic Communications in Probability (Search for Journal in Brave)

zbMATH Keywords

optimizationstochastic differential equationsrandom matrix theorystochastic gradient descent

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Inequalities; stochastic orderings (60E15) Applications of stochastic analysis (to PDEs, etc.) (60H30) Iterative numerical methods for linear systems (65F10)

Cites Work

• Title not available (Why is that?)
• A note on the Hanson-Wright inequality for random vectors with dependencies
• Randomized Kaczmarz solver for noisy linear systems
• A randomized Kaczmarz algorithm with exponential convergence
• Why random reshuffling beats stochastic gradient descent
• High-Dimensional Probability
• Applied Probability and Queues
• A Stochastic Approximation Method
• The scaling limit of high-dimensional online independent component analysis

This page was built for publication: High-dimensional limit of one-pass SGD on least squares

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6597217)