Tight analyses for subgradient descent. I: Lower bounds

DOI10.5802/OJMO.31MaRDI QIDQ6633273zbMATH OpenFDO

Authors Nicholas J. A. Harvey, Chris Liaw, Sikander Randhawa

Publication date 5 November 2024

Published in OJMO. Open Journal of Mathematical Optimization (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.5802/OJMO.31

zbMATH Keywords

first-order methodsgradient descentlower bounds

Mathematics Subject Classification ID

Extreme-point and pivoting methods (90C49)

Recommendations

• Convergence rates for deterministic and stochastic subgradient methods without Lipschitz continuity
• Faster subgradient methods for functions with Hölderian growth
• New results on subgradient methods for strongly convex optimization problems with a unified analysis
• OSGA: a fast subgradient algorithm with optimal complexity
• A superlinearly convergent subgradient method for sharp semismooth problems

Cites work

• Acceleration of Stochastic Approximation by Averaging
• Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization
• Convex Analysis
• Convex analysis and monotone operator theory in Hilbert spaces
• Convexity and optimization in Banach spaces.
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• Logarithmic regret algorithms for online convex optimization
• Quasi-monotone subgradient methods for nonsmooth convex minimization

Cited in

(1)

• Exact convergence rate of the last iterate in subgradient methods

This page was built for publication: Tight analyses for subgradient descent. I: Lower bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6633273)