Nonstationary online convex optimization with multiple predictions

DOI10.1016/J.INS.2023.119862MaRDI QIDQ6151925zbMATH OpenFDO

Authors Qingxin Meng, Jianwei Liu

Publication date 12 February 2024

Published in Information Sciences (Search for Journal in Brave)

zbMATH Keywords

meta-learningoptimistic online learningdynamic regretimplicit mirror descentnon-stationary online convex optimization

Mathematics Subject Classification ID

Statistics (62-XX) Mathematical programming (90Cxx)

Recommendations

• Online composite optimization with time-varying regularizers
• Bandit convex optimization in non-stationary environments
• Predictive online convex optimization
• Second-order non-stationary online learning for regression
• Logarithmic Regret Algorithms for Online Convex Optimization

Cites work

• Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
• Exponentiated gradient versus gradient descent for linear predictors
• Non-stationary stochastic optimization
• Online learning and online convex optimization
• Proximité et dualité dans un espace hilbertien
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• Scale-free online learning
• Tracking the best linear predictor

Cited in

(1)

• Online composite optimization with time-varying regularizers

This page was built for publication: Nonstationary online convex optimization with multiple predictions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6151925)