On the parallelization upper bound for asynchronous stochastic gradients descent in non-convex optimization

DOI10.1007/S10957-022-02141-9OpenAlexW4310657725MaRDI QIDQ2696976

Lifu Wang, Bo Shen

Publication date: 17 April 2023

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10957-022-02141-9

zbMATH Keywords

non-convex optimizationdeep learningasynchronous parallel optimizationsaddle points escaping

Mathematics Subject Classification ID

Mathematical programming (90Cxx) Calculus of variations and optimal control; optimization (49-XX)

Uses Software

• HOGWILD

Cites Work

• Unnamed Item
• Multivariate trace inequalities
• Razumikhin-type theorems on exponential stability of stochastic functional differential equations
• Razumikhin-type theorems on exponential stability of neutral stochastic functional differential equations
• Convex trace functions and the Wigner-Yanase-Dyson conjecture
• Optimal Distributed Online Prediction using Mini-Batches
• An Asynchronous Parallel Stochastic Coordinate Descent Algorithm

This page was built for publication: On the parallelization upper bound for asynchronous stochastic gradients descent in non-convex optimization