Asynchronous Parallel Nonconvex Optimization Under the Polyak-Łojasiewicz Condition

Communication delays and synchronization are major bottlenecks for parallel computing, and tolerating asynchrony is therefore crucial for accelerating parallel computation. Motivated by optimization problems that do not satisfy convexity assumptions, we present an asynchronous block coordinate desce...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE control systems letters Ročník 6; s. 524 - 529
Hlavní autoři: Yazdani, Kasra, Hale, Matthew
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 2022
Témata:
asynchronous optimization algorithms
Convergence
Delays
Linear programming
Machine learning algorithms
multi-agent systems
nonconvex optimization
Optimization
Parallel computation
Program processors
Signal processing algorithms
ISSN:2475-1456, 2475-1456
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Communication delays and synchronization are major bottlenecks for parallel computing, and tolerating asynchrony is therefore crucial for accelerating parallel computation. Motivated by optimization problems that do not satisfy convexity assumptions, we present an asynchronous block coordinate descent algorithm for nonconvex optimization problems whose objective functions satisfy the Polyak-Łojasiewicz condition. This condition is a generalization of strong convexity to nonconvex problems and requires neither convexity nor uniqueness of minimizers. Under only assumptions of mild smoothness of objective functions and bounded delays, we prove that a linear convergence rate is obtained. Numerical experiments for logistic regression problems are presented to illustrate the impact of asynchrony upon convergence.
ISSN:2475-1456
2475-1456
DOI:10.1109/LCSYS.2021.3082800