FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3009614481> ?p ?o ?g. }

• W3009614481 endingPage "349" @default.
• W3009614481 startingPage "317" @default.
• W3009614481 abstract "The stochastic Frank–Wolfe method has recently attracted much general interest in the context of optimization for statistical and machine learning due to its ability to work with a more general feasible region. However, there has been a complexity gap in the dependence on the optimality tolerance $$varepsilon $$ in the guaranteed convergence rate for stochastic Frank–Wolfe compared to its deterministic counterpart. In this work, we present a new generalized stochastic Frank–Wolfe method which closes this gap for the class of structured optimization problems encountered in statistical and machine learning characterized by empirical loss minimization with a certain type of “linear prediction” property (formally defined in the paper), which is typically present in loss minimization problems in practice. Our method also introduces the notion of a “substitute gradient” that is a not-necessarily-unbiased estimate of the gradient. We show that our new method is equivalent to a particular randomized coordinate mirror descent algorithm applied to the dual problem, which in turn provides a new interpretation of randomized dual coordinate descent in the primal space. Also, in the special case of a strongly convex regularizer our generalized stochastic Frank–Wolfe method (as well as the randomized dual coordinate descent method) exhibits linear convergence. Furthermore, we present computational experiments that indicate that our method outperforms other stochastic Frank–Wolfe methods for a sufficiently small optimality tolerance, consistent with the theory developed herein." @default.
• W3009614481 created "2020-03-13" @default.
• W3009614481 creator A5004737240 @default.
• W3009614481 creator A5062563819 @default.
• W3009614481 date "2020-03-04" @default.
• W3009614481 modified "2023-09-26" @default.
• W3009614481 title "Generalized stochastic Frank–Wolfe algorithm with stochastic “substitute” gradient for structured convex optimization" @default.
• W3009614481 cites W2003146967 @default.
• W3009614481 cites W2016384870 @default.
• W3009614481 cites W2075660001 @default.
• W3009614481 cites W2076095618 @default.
• W3009614481 cites W2095984592 @default.
• W3009614481 cites W2114605231 @default.
• W3009614481 cites W2117686388 @default.
• W3009614481 cites W2120717492 @default.
• W3009614481 cites W2129470876 @default.
• W3009614481 cites W2136885855 @default.
• W3009614481 cites W2141696759 @default.
• W3009614481 cites W2163786124 @default.
• W3009614481 cites W2188195356 @default.
• W3009614481 cites W2535496140 @default.
• W3009614481 cites W2551153860 @default.
• W3009614481 cites W2611328865 @default.
• W3009614481 cites W2962706047 @default.
• W3009614481 cites W2963156201 @default.
• W3009614481 cites W2963607709 @default.
• W3009614481 cites W2963663060 @default.
• W3009614481 cites W2964177174 @default.
• W3009614481 cites W3098888484 @default.
• W3009614481 cites W4234698323 @default.
• W3009614481 doi "https://doi.org/10.1007/s10107-020-01480-7" @default.
• W3009614481 hasPublicationYear "2020" @default.
• W3009614481 type Work @default.
• W3009614481 sameAs 3009614481 @default.
• W3009614481 citedByCount "11" @default.
• W3009614481 countsByYear W30096144812020 @default.
• W3009614481 countsByYear W30096144812021 @default.
• W3009614481 countsByYear W30096144812022 @default.
• W3009614481 countsByYear W30096144812023 @default.
• W3009614481 crossrefType "journal-article" @default.
• W3009614481 hasAuthorship W3009614481A5004737240 @default.
• W3009614481 hasAuthorship W3009614481A5062563819 @default.
• W3009614481 hasBestOaLocation W30096144812 @default.
• W3009614481 hasConcept C112680207 @default.
• W3009614481 hasConcept C126255220 @default.
• W3009614481 hasConcept C127162648 @default.
• W3009614481 hasConcept C151730666 @default.
• W3009614481 hasConcept C154945302 @default.
• W3009614481 hasConcept C157972887 @default.
• W3009614481 hasConcept C162324750 @default.
• W3009614481 hasConcept C194387892 @default.
• W3009614481 hasConcept C206688291 @default.
• W3009614481 hasConcept C2524010 @default.
• W3009614481 hasConcept C2777303404 @default.
• W3009614481 hasConcept C2779343474 @default.
• W3009614481 hasConcept C31258907 @default.
• W3009614481 hasConcept C33923547 @default.
• W3009614481 hasConcept C41008148 @default.
• W3009614481 hasConcept C50522688 @default.
• W3009614481 hasConcept C50644808 @default.
• W3009614481 hasConcept C57869625 @default.
• W3009614481 hasConcept C86803240 @default.
• W3009614481 hasConceptScore W3009614481C112680207 @default.
• W3009614481 hasConceptScore W3009614481C126255220 @default.
• W3009614481 hasConceptScore W3009614481C127162648 @default.
• W3009614481 hasConceptScore W3009614481C151730666 @default.
• W3009614481 hasConceptScore W3009614481C154945302 @default.
• W3009614481 hasConceptScore W3009614481C157972887 @default.
• W3009614481 hasConceptScore W3009614481C162324750 @default.
• W3009614481 hasConceptScore W3009614481C194387892 @default.
• W3009614481 hasConceptScore W3009614481C206688291 @default.
• W3009614481 hasConceptScore W3009614481C2524010 @default.
• W3009614481 hasConceptScore W3009614481C2777303404 @default.
• W3009614481 hasConceptScore W3009614481C2779343474 @default.
• W3009614481 hasConceptScore W3009614481C31258907 @default.
• W3009614481 hasConceptScore W3009614481C33923547 @default.
• W3009614481 hasConceptScore W3009614481C41008148 @default.
• W3009614481 hasConceptScore W3009614481C50522688 @default.
• W3009614481 hasConceptScore W3009614481C50644808 @default.
• W3009614481 hasConceptScore W3009614481C57869625 @default.
• W3009614481 hasConceptScore W3009614481C86803240 @default.
• W3009614481 hasFunder F4320332467 @default.
• W3009614481 hasIssue "1-2" @default.
• W3009614481 hasLocation W30096144811 @default.
• W3009614481 hasLocation W30096144812 @default.
• W3009614481 hasLocation W30096144813 @default.
• W3009614481 hasOpenAccess W3009614481 @default.
• W3009614481 hasPrimaryLocation W30096144811 @default.
• W3009614481 hasRelatedWork W1975768153 @default.
• W3009614481 hasRelatedWork W2075181955 @default.
• W3009614481 hasRelatedWork W2170262790 @default.
• W3009614481 hasRelatedWork W2398337421 @default.
• W3009614481 hasRelatedWork W2561261090 @default.
• W3009614481 hasRelatedWork W2952048857 @default.
• W3009614481 hasRelatedWork W2963896198 @default.
• W3009614481 hasRelatedWork W3024083111 @default.
• W3009614481 hasRelatedWork W3186075884 @default.
• W3009614481 hasRelatedWork W4213455174 @default.

• next