Uniform-in-time weak error analysis for stochastic gradient descent algorithms via diffusion approximation

DOI10.4310/CMS.2020.v18.n1.a7zbMath1440.60073arXiv1902.00635OpenAlexW3014365854MaRDI QIDQ1984706

Tingran Gao, Yuanyuan Feng, Yulong Lu, Lei Li, Jian-Guo Liu

Publication date: 7 April 2020

Published in: Communications in Mathematical Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1902.00635

zbMATH Keywords

stochastic differential equationdiffusion approximationstochastic gradient descentbackward Kolmogorov equationweak error analysis

Mathematics Subject Classification ID

Stochastic programming (90C15) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20)

Related Items (3)

Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations ⋮ A probability approximation framework: Markov process approach ⋮ Analysis of kinetic models for label switching and stochastic gradient descent

This page was built for publication: Uniform-in-time weak error analysis for stochastic gradient descent algorithms via diffusion approximation