FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201945250> ?p ?o ?g. }

• W3201945250 endingPage "5380" @default.
• W3201945250 startingPage "5366" @default.
• W3201945250 abstract "In this article, we propose a novel solution for nonconvex problems of multiple variables, especially for those typically solved by an alternating minimization (AM) strategy that splits the original optimization problem into a set of subproblems corresponding to each variable and then iteratively optimizes each subproblem using a fixed updating rule. However, due to the intrinsic nonconvexity of the original optimization problem, the optimization can be trapped into a spurious local minimum even when each subproblem can be optimally solved at each iteration. Meanwhile, learning-based approaches, such as deep unfolding algorithms, have gained popularity for nonconvex optimization; however, they are highly limited by the availability of labeled data and insufficient explainability. To tackle these issues, we propose a meta-learning based alternating minimization (MLAM) method that aims to minimize a part of the global losses over iterations instead of carrying minimization on each subproblem, and it tends to learn an adaptive strategy to replace the handcrafted counterpart resulting in advance on superior performance. The proposed MLAM maintains the original algorithmic principle, providing certain interpretability. We evaluate the proposed method on two representative problems, namely, bilinear inverse problem: matrix completion and nonlinear problem: Gaussian mixture models. The experimental results validate the proposed approach outperforms AM-based methods." @default.
• W3201945250 created "2021-10-11" @default.
• W3201945250 creator A5008353732 @default.
• W3201945250 creator A5016883501 @default.
• W3201945250 creator A5030729311 @default.
• W3201945250 creator A5037501616 @default.
• W3201945250 creator A5078507701 @default.
• W3201945250 creator A5083334628 @default.
• W3201945250 date "2023-09-01" @default.
• W3201945250 modified "2023-10-17" @default.
• W3201945250 title "Metalearning-Based Alternating Minimization Algorithm for Nonconvex Optimization" @default.
• W3201945250 cites W1511814458 @default.
• W3201945250 cites W1890834058 @default.
• W3201945250 cites W1976618413 @default.
• W3201945250 cites W1979089199 @default.
• W3201945250 cites W1980147176 @default.
• W3201945250 cites W1981367467 @default.
• W3201945250 cites W1991042426 @default.
• W3201945250 cites W1994427954 @default.
• W3201945250 cites W2010286849 @default.
• W3201945250 cites W2025301163 @default.
• W3201945250 cites W2035466430 @default.
• W3201945250 cites W2047064469 @default.
• W3201945250 cites W2054141820 @default.
• W3201945250 cites W2060204507 @default.
• W3201945250 cites W2064675550 @default.
• W3201945250 cites W2106005123 @default.
• W3201945250 cites W2110606453 @default.
• W3201945250 cites W2134199473 @default.
• W3201945250 cites W2143570353 @default.
• W3201945250 cites W2150355110 @default.
• W3201945250 cites W2160547390 @default.
• W3201945250 cites W2194775991 @default.
• W3201945250 cites W2225747377 @default.
• W3201945250 cites W2503339013 @default.
• W3201945250 cites W2609983914 @default.
• W3201945250 cites W2611328865 @default.
• W3201945250 cites W2745949522 @default.
• W3201945250 cites W2765145408 @default.
• W3201945250 cites W2921392200 @default.
• W3201945250 cites W2935808773 @default.
• W3201945250 cites W2963972677 @default.
• W3201945250 cites W2998292532 @default.
• W3201945250 cites W3011423728 @default.
• W3201945250 cites W3030509278 @default.
• W3201945250 cites W3034724715 @default.
• W3201945250 cites W3035302306 @default.
• W3201945250 cites W3080597126 @default.
• W3201945250 cites W3085935744 @default.
• W3201945250 cites W3087868801 @default.
• W3201945250 cites W3096252532 @default.
• W3201945250 cites W3104501706 @default.
• W3201945250 cites W3163573064 @default.
• W3201945250 cites W3188921881 @default.
• W3201945250 cites W3194370280 @default.
• W3201945250 cites W3196467959 @default.
• W3201945250 cites W4300672471 @default.
• W3201945250 doi "https://doi.org/10.1109/tnnls.2022.3165627" @default.
• W3201945250 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35439147" @default.
• W3201945250 hasPublicationYear "2023" @default.
• W3201945250 type Work @default.
• W3201945250 sameAs 3201945250 @default.
• W3201945250 citedByCount "9" @default.
• W3201945250 countsByYear W32019452502022 @default.
• W3201945250 countsByYear W32019452502023 @default.
• W3201945250 crossrefType "journal-article" @default.
• W3201945250 hasAuthorship W3201945250A5008353732 @default.
• W3201945250 hasAuthorship W3201945250A5016883501 @default.
• W3201945250 hasAuthorship W3201945250A5030729311 @default.
• W3201945250 hasAuthorship W3201945250A5037501616 @default.
• W3201945250 hasAuthorship W3201945250A5078507701 @default.
• W3201945250 hasAuthorship W3201945250A5083334628 @default.
• W3201945250 hasBestOaLocation W32019452502 @default.
• W3201945250 hasConcept C11413529 @default.
• W3201945250 hasConcept C119857082 @default.
• W3201945250 hasConcept C126255220 @default.
• W3201945250 hasConcept C137836250 @default.
• W3201945250 hasConcept C147764199 @default.
• W3201945250 hasConcept C154945302 @default.
• W3201945250 hasConcept C205203396 @default.
• W3201945250 hasConcept C2781067378 @default.
• W3201945250 hasConcept C31972630 @default.
• W3201945250 hasConcept C33923547 @default.
• W3201945250 hasConcept C41008148 @default.
• W3201945250 hasConcept C97256817 @default.
• W3201945250 hasConceptScore W3201945250C11413529 @default.
• W3201945250 hasConceptScore W3201945250C119857082 @default.
• W3201945250 hasConceptScore W3201945250C126255220 @default.
• W3201945250 hasConceptScore W3201945250C137836250 @default.
• W3201945250 hasConceptScore W3201945250C147764199 @default.
• W3201945250 hasConceptScore W3201945250C154945302 @default.
• W3201945250 hasConceptScore W3201945250C205203396 @default.
• W3201945250 hasConceptScore W3201945250C2781067378 @default.
• W3201945250 hasConceptScore W3201945250C31972630 @default.
• W3201945250 hasConceptScore W3201945250C33923547 @default.
• W3201945250 hasConceptScore W3201945250C41008148 @default.
• W3201945250 hasConceptScore W3201945250C97256817 @default.
• W3201945250 hasFunder F4320321001 @default.

• next