On the oracle complexity of smooth strongly convex minimization

We construct a family of functions suitable for establishing lower bounds on the oracle complexity of first-order minimization of smooth strongly-convex functions. Based on this construction, we derive new lower bounds on the complexity of strongly-convex minimization under various inaccuracy criter...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Journal of Complexity Ročník 68; s. 101590
Hlavní autori:	Drori, Yoel, Taylor, Adrien
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier Inc 01.02.2022 Elsevier
Predmet:	Information-based complexity Mathematics Optimal methods Optimization and Control Oracle complexity Strongly convex functions Strongly convex functions Optimal methods Oracle complexity Information-based complexity
ISSN:	0885-064X, 1090-2708
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	We construct a family of functions suitable for establishing lower bounds on the oracle complexity of first-order minimization of smooth strongly-convex functions. Based on this construction, we derive new lower bounds on the complexity of strongly-convex minimization under various inaccuracy criteria. The new bounds match the known upper bounds up to a constant factor, and when the inaccuracy of a solution is measured by its distance to the solution set, the new lower bound exactly matches the upper bound obtained by the recent Information-Theoretic Exact Method by the same authors, thereby establishing the exact oracle complexity for this class of problems.
ISSN:	0885-064X 1090-2708
DOI:	10.1016/j.jco.2021.101590