Hyperfast second-order local solvers for efficient statistically preconditioned distributed optimization

Statistical preconditioning enables fast methods for distributed large-scale empirical risk minimization problems. In this approach, multiple worker nodes compute gradients in parallel, which are then used by the central node to update the parameter by solving an auxiliary (preconditioned) smaller-s...

Celý popis

Podrobná bibliografia

Vydané v:	EURO journal on computational optimization Ročník 10; s. 100045
Hlavní autori:	Dvurechensky, Pavel, Kamzolov, Dmitry, Lukashevich, Aleksandr, Lee, Soomin, Ordentlich, Erik, Uribe, César A., Gasnikov, Alexander
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier Ltd 2022 Elsevier
Predmet:	Distributed optimization Empirical risk minimization Statistical preconditioning Tensor optimization methods Empirical risk minimization Distributed optimization Tensor optimization methods Statistical preconditioning
ISSN:	2192-4406
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!