Second-order guarantees in centralized, federated and decentralized nonconvex optimization

MaRDI QIDQ2225211zbMATH OpenFDO

Authors Stefan Vlaski, Ali H. Sayed

Publication date 5 February 2021

Published in Communications in Information and Systems (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2003.14366

zbMATH Keywords

gradient perturbationsstochastic first-order optimization algorithms

Mathematics Subject Classification ID

Neural nets and related approaches to inference from stochastic processes (62M45) Statistical aspects of big data and data science (62R07) Nonconvex programming, global optimization (90C26)

Recommendations

• Second-order guarantees of distributed gradient algorithms
• On Nonconvex Optimization for Machine Learning
• Accelerated methods for nonconvex optimization
• Finding approximate local minima faster than gradient descent
• On the Divergence of Decentralized Nonconvex Optimization

Cited in

(7)

• On the Divergence of Decentralized Nonconvex Optimization
• On Nonconvex Optimization for Machine Learning
• Second-order guarantees of distributed gradient algorithms
• Second-Order Guarantees of Stochastic Gradient Descent in Nonconvex Optimization
• Decentralized nonconvex optimization with guaranteed privacy and accuracy
• Second-Order Guarantees in Centralized, Federated and Decentralized Nonconvex Optimization
• Recent Theoretical Advances in Non-Convex Optimization

This page was built for publication: Second-order guarantees in centralized, federated and decentralized nonconvex optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2225211)