Potential-function proofs for gradient methods

DOI10.4086/TOC.2019.V015A004MaRDI QIDQ5204822zbMATH OpenOpenAlexFDO

Authors N. Bansal, Anupam Gupta

Publication date 5 December 2019

Published in Theory of Computing (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.4086/toc.2019.v015a004

zbMATH Keywords

convex optimizationpotential function

Mathematics Subject Classification ID

Convex programming (90C25) Methods of reduced gradient type (90C52)

Recommendations

• Convergence of first-order methods via the convex conjugate
• On the convergence analysis of the optimized gradient method
• Potential Function-Based Framework for Minimizing Gradients in Convex and Min-Max Optimization
• Gradient Convergence in Gradient methods with Errors
• First-order methods for convex optimization

Cited in

(10)

• The regularized submodular maximization via the Lyapunov method
• A Systematic Approach to Lyapunov Analyses of Continuous-Time Models in Convex Optimization
• A Laplacian approach to \(\ell_1\)-norm minimization
• The rate of convergence of optimization algorithms obtained via discretizations of heavy ball dynamical systems for convex optimization problems
• Recent theoretical advances in decentralized distributed convex optimization
• An optimal gradient method for smooth strongly convex minimization
• No-regret algorithms in on-line learning, games and convex optimization
• A note on approximate accelerated forward-backward methods with absolute and relative errors, and possibly strongly convex objectives
• Potential Function-Based Framework for Minimizing Gradients in Convex and Min-Max Optimization
• Factor-\(\sqrt{2}\) acceleration of accelerated gradient methods

This page was built for publication: Potential-function proofs for gradient methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5204822)