A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds

zbMath1403.68193arXiv1709.02726MaRDI QIDQ4645676

Csaba Szepesvári, Pooria Joulani, András György

Publication date: 10 January 2019

Full work available at URL: https://arxiv.org/abs/1709.02726

zbMATH Keywords

stochastic optimizationonline learningnon-convex optimizationimplicit updatesfollow-the-regularized-leadermirror-descentoptimistic online learningsmooth lossesstrongly convex learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Online algorithms; streaming algorithms (68W27)

This page was built for publication: A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds