Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308991248> ?p ?o ?g. }
- W4308991248 endingPage "103819" @default.
- W4308991248 startingPage "103819" @default.
- W4308991248 abstract "We reformulate unsupervised dimension reduction problem (UDR) in the language of tempered distributions, i.e. as a problem of approximating an empirical probability density function by another tempered distribution, supported in a k-dimensional subspace. We show that this task is connected with another classical problem of data science — the sufficient dimension reduction problem (SDR). In fact, an algorithm for the first problem induces an algorithm for the second and vice versa. In order to reduce an optimization problem over distributions to an optimization problem over ordinary functions we introduce a nonnegative penalty function that “forces” the support of the model distribution to be k-dimensional. Then we present an algorithm for the minimization of the penalized objective, based on the infinite-dimensional low-rank optimization, which we call the alternating scheme. Also, we design an efficient approximate algorithm for a special case of the problem, where the distance between the empirical distribution and the model distribution is measured by Maximum Mean Discrepancy defined by a Mercer kernel of a certain type. We test our methods on four examples (three UDR and one SDR) using synthetic data and standard datasets." @default.
- W4308991248 created "2022-11-20" @default.
- W4308991248 creator A5029285634 @default.
- W4308991248 date "2023-03-01" @default.
- W4308991248 modified "2023-09-29" @default.
- W4308991248 title "Reducing the dimensionality of data using tempered distributions" @default.
- W4308991248 cites W1480330138 @default.
- W4308991248 cites W1482071412 @default.
- W4308991248 cites W1644425553 @default.
- W4308991248 cites W1969698720 @default.
- W4308991248 cites W2005482089 @default.
- W4308991248 cites W2010361836 @default.
- W4308991248 cites W2012411663 @default.
- W4308991248 cites W2073031580 @default.
- W4308991248 cites W2079784933 @default.
- W4308991248 cites W2081566336 @default.
- W4308991248 cites W2087717467 @default.
- W4308991248 cites W2123921160 @default.
- W4308991248 cites W2144405862 @default.
- W4308991248 cites W2145962650 @default.
- W4308991248 cites W2163490846 @default.
- W4308991248 cites W2166116275 @default.
- W4308991248 cites W2189846329 @default.
- W4308991248 cites W2198863840 @default.
- W4308991248 cites W2418306335 @default.
- W4308991248 cites W2741989487 @default.
- W4308991248 cites W2750950678 @default.
- W4308991248 cites W3105973667 @default.
- W4308991248 cites W3213321178 @default.
- W4308991248 cites W4206348101 @default.
- W4308991248 cites W649348608 @default.
- W4308991248 cites W792141054 @default.
- W4308991248 doi "https://doi.org/10.1016/j.dsp.2022.103819" @default.
- W4308991248 hasPublicationYear "2023" @default.
- W4308991248 type Work @default.
- W4308991248 citedByCount "0" @default.
- W4308991248 crossrefType "journal-article" @default.
- W4308991248 hasAuthorship W4308991248A5029285634 @default.
- W4308991248 hasBestOaLocation W43089912482 @default.
- W4308991248 hasConcept C105795698 @default.
- W4308991248 hasConcept C110121322 @default.
- W4308991248 hasConcept C111030470 @default.
- W4308991248 hasConcept C111335779 @default.
- W4308991248 hasConcept C11413529 @default.
- W4308991248 hasConcept C114614502 @default.
- W4308991248 hasConcept C118615104 @default.
- W4308991248 hasConcept C126255220 @default.
- W4308991248 hasConcept C134306372 @default.
- W4308991248 hasConcept C137836250 @default.
- W4308991248 hasConcept C14036430 @default.
- W4308991248 hasConcept C149441793 @default.
- W4308991248 hasConcept C154945302 @default.
- W4308991248 hasConcept C197055811 @default.
- W4308991248 hasConcept C2524010 @default.
- W4308991248 hasConcept C28826006 @default.
- W4308991248 hasConcept C32834561 @default.
- W4308991248 hasConcept C33676613 @default.
- W4308991248 hasConcept C33923547 @default.
- W4308991248 hasConcept C41008148 @default.
- W4308991248 hasConcept C6180225 @default.
- W4308991248 hasConcept C70518039 @default.
- W4308991248 hasConcept C74193536 @default.
- W4308991248 hasConcept C78458016 @default.
- W4308991248 hasConcept C86803240 @default.
- W4308991248 hasConcept C98385598 @default.
- W4308991248 hasConceptScore W4308991248C105795698 @default.
- W4308991248 hasConceptScore W4308991248C110121322 @default.
- W4308991248 hasConceptScore W4308991248C111030470 @default.
- W4308991248 hasConceptScore W4308991248C111335779 @default.
- W4308991248 hasConceptScore W4308991248C11413529 @default.
- W4308991248 hasConceptScore W4308991248C114614502 @default.
- W4308991248 hasConceptScore W4308991248C118615104 @default.
- W4308991248 hasConceptScore W4308991248C126255220 @default.
- W4308991248 hasConceptScore W4308991248C134306372 @default.
- W4308991248 hasConceptScore W4308991248C137836250 @default.
- W4308991248 hasConceptScore W4308991248C14036430 @default.
- W4308991248 hasConceptScore W4308991248C149441793 @default.
- W4308991248 hasConceptScore W4308991248C154945302 @default.
- W4308991248 hasConceptScore W4308991248C197055811 @default.
- W4308991248 hasConceptScore W4308991248C2524010 @default.
- W4308991248 hasConceptScore W4308991248C28826006 @default.
- W4308991248 hasConceptScore W4308991248C32834561 @default.
- W4308991248 hasConceptScore W4308991248C33676613 @default.
- W4308991248 hasConceptScore W4308991248C33923547 @default.
- W4308991248 hasConceptScore W4308991248C41008148 @default.
- W4308991248 hasConceptScore W4308991248C6180225 @default.
- W4308991248 hasConceptScore W4308991248C70518039 @default.
- W4308991248 hasConceptScore W4308991248C74193536 @default.
- W4308991248 hasConceptScore W4308991248C78458016 @default.
- W4308991248 hasConceptScore W4308991248C86803240 @default.
- W4308991248 hasConceptScore W4308991248C98385598 @default.
- W4308991248 hasLocation W43089912481 @default.
- W4308991248 hasLocation W43089912482 @default.
- W4308991248 hasOpenAccess W4308991248 @default.
- W4308991248 hasPrimaryLocation W43089912481 @default.
- W4308991248 hasRelatedWork W1983402934 @default.
- W4308991248 hasRelatedWork W2014040967 @default.
- W4308991248 hasRelatedWork W2107793823 @default.