Noise amplifiation of momentum-based optimization algorithms

We study momentum-based first-order optimization algorithms in which the iterations utilize information from the two previous steps and are subject to additive white noise. For strongly convex quadratic problems, we utilize Jury stability criterion to provide a novel geometric characterization of li...

Celý popis

Podrobná bibliografia

Vydané v:	Proceedings of the American Control Conference s. 849 - 854
Hlavní autori:	Mohammadi, Hesameddin, Razaviyayn, Meisam, Jovanovic, Mihailo R.
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	American Automatic Control Council 31.05.2023
Predmet:	Additive white noise Convergence convergence rate convex optimization First-order methods heavy-ball method Nesterov's accelerated algorithm noise amplification Optimization performance tradeoffs settling time Stability criteria Steady-state
ISSN:	2378-5861
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!