Matches in SemOpenAlex for { <https://semopenalex.org/work/W3064479281> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3064479281 endingPage "816" @default.
- W3064479281 startingPage "777" @default.
- W3064479281 abstract "Grassmann manifold based sparse spectral clustering is a classification technique that consists in learning a latent representation of data, formed by a subspace basis, which is sparse. In order to learn a latent representation, spectral clustering is formulated in terms of a loss minimization problem over a smooth manifold known as Grassmannian. Such minimization problem cannot be tackled by one of traditional gradient-based learning algorithms, which are only suitable to perform optimization in absence of constraints among parameters. It is, therefore, necessary to develop specific optimization/learning algorithms that are able to look for a local minimum of a loss function under smooth constraints in an efficient way. Such need calls for manifold optimization methods. In this paper, we extend classical gradient-based learning algorithms on at parameter spaces (from classical gradient descent to adaptive momentum) to curved spaces (smooth manifolds) by means of tools from manifold calculus. We compare clustering performances of these methods and known methods from the scientific literature. The obtained results confirm that the proposed learning algorithms prove lighter in computational complexity than existing ones without detriment in clustering efficacy." @default.
- W3064479281 created "2020-08-24" @default.
- W3064479281 creator A5079056700 @default.
- W3064479281 creator A5083365850 @default.
- W3064479281 date "2020-08-17" @default.
- W3064479281 modified "2023-10-10" @default.
- W3064479281 title "Gradient-based Learning Methods Extended to Smooth Manifolds Applied to Automated Clustering" @default.
- W3064479281 doi "https://doi.org/10.1613/jair.1.12192" @default.
- W3064479281 hasPublicationYear "2020" @default.
- W3064479281 type Work @default.
- W3064479281 sameAs 3064479281 @default.
- W3064479281 citedByCount "3" @default.
- W3064479281 countsByYear W30644792812021 @default.
- W3064479281 countsByYear W30644792812022 @default.
- W3064479281 crossrefType "journal-article" @default.
- W3064479281 hasAuthorship W3064479281A5079056700 @default.
- W3064479281 hasAuthorship W3064479281A5083365850 @default.
- W3064479281 hasBestOaLocation W30644792811 @default.
- W3064479281 hasConcept C105611402 @default.
- W3064479281 hasConcept C11413529 @default.
- W3064479281 hasConcept C114614502 @default.
- W3064479281 hasConcept C126255220 @default.
- W3064479281 hasConcept C127413603 @default.
- W3064479281 hasConcept C153258448 @default.
- W3064479281 hasConcept C154945302 @default.
- W3064479281 hasConcept C162929932 @default.
- W3064479281 hasConcept C17744445 @default.
- W3064479281 hasConcept C199539241 @default.
- W3064479281 hasConcept C2776359362 @default.
- W3064479281 hasConcept C32834561 @default.
- W3064479281 hasConcept C33923547 @default.
- W3064479281 hasConcept C41008148 @default.
- W3064479281 hasConcept C50644808 @default.
- W3064479281 hasConcept C529865628 @default.
- W3064479281 hasConcept C73555534 @default.
- W3064479281 hasConcept C78519656 @default.
- W3064479281 hasConcept C94625758 @default.
- W3064479281 hasConceptScore W3064479281C105611402 @default.
- W3064479281 hasConceptScore W3064479281C11413529 @default.
- W3064479281 hasConceptScore W3064479281C114614502 @default.
- W3064479281 hasConceptScore W3064479281C126255220 @default.
- W3064479281 hasConceptScore W3064479281C127413603 @default.
- W3064479281 hasConceptScore W3064479281C153258448 @default.
- W3064479281 hasConceptScore W3064479281C154945302 @default.
- W3064479281 hasConceptScore W3064479281C162929932 @default.
- W3064479281 hasConceptScore W3064479281C17744445 @default.
- W3064479281 hasConceptScore W3064479281C199539241 @default.
- W3064479281 hasConceptScore W3064479281C2776359362 @default.
- W3064479281 hasConceptScore W3064479281C32834561 @default.
- W3064479281 hasConceptScore W3064479281C33923547 @default.
- W3064479281 hasConceptScore W3064479281C41008148 @default.
- W3064479281 hasConceptScore W3064479281C50644808 @default.
- W3064479281 hasConceptScore W3064479281C529865628 @default.
- W3064479281 hasConceptScore W3064479281C73555534 @default.
- W3064479281 hasConceptScore W3064479281C78519656 @default.
- W3064479281 hasConceptScore W3064479281C94625758 @default.
- W3064479281 hasLocation W30644792811 @default.
- W3064479281 hasOpenAccess W3064479281 @default.
- W3064479281 hasPrimaryLocation W30644792811 @default.
- W3064479281 hasRelatedWork W1524747314 @default.
- W3064479281 hasRelatedWork W1543726458 @default.
- W3064479281 hasRelatedWork W1960721387 @default.
- W3064479281 hasRelatedWork W2088025572 @default.
- W3064479281 hasRelatedWork W2363376159 @default.
- W3064479281 hasRelatedWork W2902286210 @default.
- W3064479281 hasRelatedWork W2951182714 @default.
- W3064479281 hasRelatedWork W4281391697 @default.
- W3064479281 hasRelatedWork W4292166970 @default.
- W3064479281 hasRelatedWork W2112228809 @default.
- W3064479281 hasVolume "68" @default.
- W3064479281 isParatext "false" @default.
- W3064479281 isRetracted "false" @default.
- W3064479281 magId "3064479281" @default.
- W3064479281 workType "article" @default.