New analysis and results for the Frank–Wolfe method

We present new results for the Frank–Wolfe method (also known as the conditional gradient method). We derive computational guarantees for arbitrary step-size sequences, which are then applied to various step-size rules, including simple averaging and constant step-sizes. We also develop step-size ru...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Mathematical programming Ročník 155; číslo 1-2; s. 199 - 230
Hlavní autoři:	Freund, Robert M., Grigas, Paul
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Berlin/Heidelberg Springer Berlin Heidelberg 01.01.2016 Springer Nature B.V
Témata:	Accuracy Approximation Calculus of Variations and Optimal Control; Optimization Combinatorics Computation Constants Convex analysis Full Length Paper Mathematical analysis Mathematical and Computational Physics Mathematical Methods in Physics Mathematical models Mathematical programming Mathematics Mathematics and Statistics Mathematics of Computing Methods Numerical Analysis Optimization Scholarships & fellowships Sequences Sparsity Studies Theoretical 90C06 90C25 65K05
ISSN:	0025-5610, 1436-4646
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!