SwePub
Sök i LIBRIS databas

  Extended search

onr:"swepub:oai:DiVA.org:umu-192720"
 

Search: onr:"swepub:oai:DiVA.org:umu-192720" > Faster One-Sample S...

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist

Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization

Dresdner, Gideon (author)
Vladarean, Maria-Luiza (author)
Rätsch, Gunnar (author)
show more...
Locatello, Francesco (author)
Cevher, Volkan (author)
Yurtsever, Alp (author)
Umeå universitet,Institutionen för matematik och matematisk statistik
show less...
 (creator_code:org_t)
PMLR, 2022
2022
English.
In: Proceedings of The 25th International Conference on Artificial Intelligence and Statistics. - : PMLR.
  • Conference paper (peer-reviewed)
Abstract Subject headings
Close  
  • We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this template either suffer from slow convergence rates, or require carefully increasing the batch size over the course of the algorithm's execution, which leads to computing full gradients. In contrast, the proposed method, equipped with a stochastic average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques. In applications we put special emphasis on problems with a large number of separable constraints. Such problems are prevalent among semidefinite programming (SDP) formulations arising in machine learning and theoretical computer science. We provide numerical experiments on matrix completion, unsupervised clustering, and sparsest-cut SDPs.

Subject headings

NATURVETENSKAP  -- Matematik -- Beräkningsmatematik (hsv//swe)
NATURAL SCIENCES  -- Mathematics -- Computational Mathematics (hsv//eng)

Keyword

conditional gradient method
Frank-Wolfe
convex optimization
composite optimization
stochastic optimization
stochastic constraints
variance reduction
stochastic average gradient
semidefinite programming

Publication and Content Type

ref (subject category)
kon (subject category)

To the university's database

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist

Find more in SwePub

By the author/editor
Dresdner, Gideon
Vladarean, Maria ...
Rätsch, Gunnar
Locatello, Franc ...
Cevher, Volkan
Yurtsever, Alp
About the subject
NATURAL SCIENCES
NATURAL SCIENCES
and Mathematics
and Computational Ma ...
Articles in the publication
By the university
Umeå University

Search outside SwePub

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Close

Copy and save the link in order to return to this view