Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289596327> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4289596327 endingPage "351" @default.
- W4289596327 startingPage "334" @default.
- W4289596327 abstract "We study in this paper several problems at the intersection of decentralized optimization and online learning. Decentralized optimization plays a vital role in machine learning and has recently garnered much attention due to its inherent advantage in handling edge computations. Many decentralized optimization algorithms, both projection and projection-free algorithms with theoretical guarantees, have been proposed in the literature, focusing mainly on offline settings. However, for most real-world machine learning problems, the data is often revealed online, for example, in the case of recommender systems, image/video processing, and stock portfolio management. Therefore, in this work, we study decentralized optimization within the framework of online settings with constraints imposed on the optimization solutions (e.g., sparsity or low rank of matrices). More specifically, we consider the problem of optimizing an aggregate of convex loss functions that arrive over time such that their components are distributed over a connected network. We present a consensus-based online decentralized Frank-Wolfe algorithm that uses stochastic gradient estimates, which achieves an asymptotically tight regret guarantee of O(T) where T is a given time horizon. Furthermore, we demonstrate the performance of this algorithm for optimizing the online multiclass logistic regression model on real-world standard image datasets (MNIST, CIFAR10) by comparing with centralized online algorithms. We achieve better regret bounds than the previously best-known decentralized constrained online algorithms." @default.
- W4289596327 created "2022-08-03" @default.
- W4289596327 creator A5010500666 @default.
- W4289596327 creator A5012405751 @default.
- W4289596327 creator A5017327684 @default.
- W4289596327 creator A5077796278 @default.
- W4289596327 date "2022-11-01" @default.
- W4289596327 modified "2023-10-10" @default.
- W4289596327 title "A stochastic conditional gradient algorithm for decentralized online convex optimization" @default.
- W4289596327 cites W1540376964 @default.
- W4289596327 cites W1616857247 @default.
- W4289596327 cites W2012812921 @default.
- W4289596327 cites W2059283452 @default.
- W4289596327 cites W2112796928 @default.
- W4289596327 cites W2124608575 @default.
- W4289596327 cites W2138309709 @default.
- W4289596327 cites W2140655807 @default.
- W4289596327 cites W2149778463 @default.
- W4289596327 cites W2199097987 @default.
- W4289596327 cites W2779248810 @default.
- W4289596327 cites W2965142130 @default.
- W4289596327 cites W3102661755 @default.
- W4289596327 cites W3103802018 @default.
- W4289596327 cites W3104871901 @default.
- W4289596327 cites W4205841652 @default.
- W4289596327 doi "https://doi.org/10.1016/j.jpdc.2022.07.010" @default.
- W4289596327 hasPublicationYear "2022" @default.
- W4289596327 type Work @default.
- W4289596327 citedByCount "1" @default.
- W4289596327 countsByYear W42895963272023 @default.
- W4289596327 crossrefType "journal-article" @default.
- W4289596327 hasAuthorship W4289596327A5010500666 @default.
- W4289596327 hasAuthorship W4289596327A5012405751 @default.
- W4289596327 hasAuthorship W4289596327A5017327684 @default.
- W4289596327 hasAuthorship W4289596327A5077796278 @default.
- W4289596327 hasConcept C108583219 @default.
- W4289596327 hasConcept C112680207 @default.
- W4289596327 hasConcept C11413529 @default.
- W4289596327 hasConcept C119857082 @default.
- W4289596327 hasConcept C126255220 @default.
- W4289596327 hasConcept C137836250 @default.
- W4289596327 hasConcept C154945302 @default.
- W4289596327 hasConcept C157972887 @default.
- W4289596327 hasConcept C190502265 @default.
- W4289596327 hasConcept C194387892 @default.
- W4289596327 hasConcept C196921405 @default.
- W4289596327 hasConcept C2524010 @default.
- W4289596327 hasConcept C33923547 @default.
- W4289596327 hasConcept C41008148 @default.
- W4289596327 hasConcept C50817715 @default.
- W4289596327 hasConceptScore W4289596327C108583219 @default.
- W4289596327 hasConceptScore W4289596327C112680207 @default.
- W4289596327 hasConceptScore W4289596327C11413529 @default.
- W4289596327 hasConceptScore W4289596327C119857082 @default.
- W4289596327 hasConceptScore W4289596327C126255220 @default.
- W4289596327 hasConceptScore W4289596327C137836250 @default.
- W4289596327 hasConceptScore W4289596327C154945302 @default.
- W4289596327 hasConceptScore W4289596327C157972887 @default.
- W4289596327 hasConceptScore W4289596327C190502265 @default.
- W4289596327 hasConceptScore W4289596327C194387892 @default.
- W4289596327 hasConceptScore W4289596327C196921405 @default.
- W4289596327 hasConceptScore W4289596327C2524010 @default.
- W4289596327 hasConceptScore W4289596327C33923547 @default.
- W4289596327 hasConceptScore W4289596327C41008148 @default.
- W4289596327 hasConceptScore W4289596327C50817715 @default.
- W4289596327 hasLocation W42895963271 @default.
- W4289596327 hasLocation W42895963272 @default.
- W4289596327 hasOpenAccess W4289596327 @default.
- W4289596327 hasPrimaryLocation W42895963271 @default.
- W4289596327 hasRelatedWork W2154682027 @default.
- W4289596327 hasRelatedWork W2590796488 @default.
- W4289596327 hasRelatedWork W2734358244 @default.
- W4289596327 hasRelatedWork W2886711096 @default.
- W4289596327 hasRelatedWork W2950475743 @default.
- W4289596327 hasRelatedWork W2994171794 @default.
- W4289596327 hasRelatedWork W3046591097 @default.
- W4289596327 hasRelatedWork W4376155396 @default.
- W4289596327 hasRelatedWork W4380078352 @default.
- W4289596327 hasRelatedWork W4386603768 @default.
- W4289596327 hasVolume "169" @default.
- W4289596327 isParatext "false" @default.
- W4289596327 isRetracted "false" @default.
- W4289596327 workType "article" @default.