FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963082572> ?p ?o ?g. }

• W2963082572 abstract "Nonnegative matrix factorization (NMF) is a popular method for audio spectral unmixing. While NMF is traditionally applied to off-the-shelf time-frequency representations based on the short-time Fourier or Cosine transforms, the ability to learn transforms from raw data attracts increasing attention. However, this adds an important computational overhead. When assumed orthogonal (like the Fourier or Cosine transforms), learning the transform yields a non-convex optimization problem on the orthogonal matrix manifold. In this paper, we derive a quasi-Newton method on the manifold using sparse approximations of the Hessian. Experiments on synthetic and real audio data show that the proposed algorithm outperforms state-of-the-art first-order and coordinate-descent methods by orders of magnitude in terms of speed. A Python package for fast TL-NMF is released online at https://github.com/pierreablin/tlnmf." @default.
• W2963082572 created "2019-07-30" @default.
• W2963082572 creator A5000651986 @default.
• W2963082572 creator A5008685312 @default.
• W2963082572 creator A5018256474 @default.
• W2963082572 creator A5022368934 @default.
• W2963082572 creator A5042340163 @default.
• W2963082572 date "2019-05-01" @default.
• W2963082572 modified "2023-10-18" @default.
• W2963082572 title "A Quasi-Newton Algorithm on the Orthogonal Manifold for NMF with Transform Learning" @default.
• W2963082572 cites W1902027874 @default.
• W2963082572 cites W1970789124 @default.
• W2963082572 cites W1988849934 @default.
• W2963082572 cites W2039844283 @default.
• W2963082572 cites W2069214509 @default.
• W2963082572 cites W2090664364 @default.
• W2963082572 cites W2104298926 @default.
• W2963082572 cites W2113154266 @default.
• W2963082572 cites W2114508388 @default.
• W2963082572 cites W2128967371 @default.
• W2963082572 cites W2162514423 @default.
• W2963082572 cites W2903219940 @default.
• W2963082572 cites W2903316710 @default.
• W2963082572 cites W2918296821 @default.
• W2963082572 cites W2962832085 @default.
• W2963082572 cites W4293775970 @default.
• W2963082572 doi "https://doi.org/10.1109/icassp.2019.8683291" @default.
• W2963082572 hasPublicationYear "2019" @default.
• W2963082572 type Work @default.
• W2963082572 sameAs 2963082572 @default.
• W2963082572 citedByCount "5" @default.
• W2963082572 countsByYear W29630825722019 @default.
• W2963082572 countsByYear W29630825722020 @default.
• W2963082572 countsByYear W29630825722022 @default.
• W2963082572 crossrefType "proceedings-article" @default.
• W2963082572 hasAuthorship W2963082572A5000651986 @default.
• W2963082572 hasAuthorship W2963082572A5008685312 @default.
• W2963082572 hasAuthorship W2963082572A5018256474 @default.
• W2963082572 hasAuthorship W2963082572A5022368934 @default.
• W2963082572 hasAuthorship W2963082572A5042340163 @default.
• W2963082572 hasBestOaLocation W29630825722 @default.
• W2963082572 hasConcept C102519508 @default.
• W2963082572 hasConcept C11413529 @default.
• W2963082572 hasConcept C115961682 @default.
• W2963082572 hasConcept C121332964 @default.
• W2963082572 hasConcept C127413603 @default.
• W2963082572 hasConcept C134306372 @default.
• W2963082572 hasConcept C152671427 @default.
• W2963082572 hasConcept C154945302 @default.
• W2963082572 hasConcept C158693339 @default.
• W2963082572 hasConcept C178009071 @default.
• W2963082572 hasConcept C203616005 @default.
• W2963082572 hasConcept C2221639 @default.
• W2963082572 hasConcept C2524010 @default.
• W2963082572 hasConcept C28826006 @default.
• W2963082572 hasConcept C33923547 @default.
• W2963082572 hasConcept C41008148 @default.
• W2963082572 hasConcept C42355184 @default.
• W2963082572 hasConcept C529865628 @default.
• W2963082572 hasConcept C62520636 @default.
• W2963082572 hasConcept C78519656 @default.
• W2963082572 hasConceptScore W2963082572C102519508 @default.
• W2963082572 hasConceptScore W2963082572C11413529 @default.
• W2963082572 hasConceptScore W2963082572C115961682 @default.
• W2963082572 hasConceptScore W2963082572C121332964 @default.
• W2963082572 hasConceptScore W2963082572C127413603 @default.
• W2963082572 hasConceptScore W2963082572C134306372 @default.
• W2963082572 hasConceptScore W2963082572C152671427 @default.
• W2963082572 hasConceptScore W2963082572C154945302 @default.
• W2963082572 hasConceptScore W2963082572C158693339 @default.
• W2963082572 hasConceptScore W2963082572C178009071 @default.
• W2963082572 hasConceptScore W2963082572C203616005 @default.
• W2963082572 hasConceptScore W2963082572C2221639 @default.
• W2963082572 hasConceptScore W2963082572C2524010 @default.
• W2963082572 hasConceptScore W2963082572C28826006 @default.
• W2963082572 hasConceptScore W2963082572C33923547 @default.
• W2963082572 hasConceptScore W2963082572C41008148 @default.
• W2963082572 hasConceptScore W2963082572C42355184 @default.
• W2963082572 hasConceptScore W2963082572C529865628 @default.
• W2963082572 hasConceptScore W2963082572C62520636 @default.
• W2963082572 hasConceptScore W2963082572C78519656 @default.
• W2963082572 hasLocation W29630825721 @default.
• W2963082572 hasLocation W29630825722 @default.
• W2963082572 hasLocation W29630825723 @default.
• W2963082572 hasLocation W29630825724 @default.
• W2963082572 hasLocation W29630825725 @default.
• W2963082572 hasLocation W29630825726 @default.
• W2963082572 hasLocation W29630825727 @default.
• W2963082572 hasOpenAccess W2963082572 @default.
• W2963082572 hasPrimaryLocation W29630825721 @default.
• W2963082572 hasRelatedWork W1095023703 @default.
• W2963082572 hasRelatedWork W1973613972 @default.
• W2963082572 hasRelatedWork W1996819670 @default.
• W2963082572 hasRelatedWork W2063166054 @default.
• W2963082572 hasRelatedWork W2127787376 @default.
• W2963082572 hasRelatedWork W2171782615 @default.
• W2963082572 hasRelatedWork W2335989979 @default.
• W2963082572 hasRelatedWork W2464819937 @default.
• W2963082572 hasRelatedWork W2760130459 @default.
• W2963082572 hasRelatedWork W4210526874 @default.

• next