Report
Huber-energy measure quantization
| Τίτλος: | Huber-energy measure quantization |
|---|---|
| Συγγραφείς: | Turinici, Gabriel |
| Στοιχεία εκδότη: | Paris |
| Έτος έκδοσης: | 2023 |
| Συλλογή: | Base Institutionnelle de Recherche de l'université Paris-Dauphine (BIRD) |
| Θεματικοί όροι: | kernel quantization, vector quantization, machine learning, database compression, Analyse |
| Time: | 519 |
| Περιγραφή: | We describe a measure quantization procedure i.e., an algorithm which finds the best approximation of a target probability law (and more generally signed finite variation measure) by a sum of Q Dirac masses (Q being the quantization parameter). The procedure is implemented by minimizing the statistical distance between the original measure and its quantized version; the distance is built from a negative definite kernel and, if necessary, can be computed on the fly and feed to a stochastic optimization algorithm (such as SGD, Adam, .). We investigate theoretically the fundamental questions of existence of the optimal measure quantizer and identify what are the required kernel properties that guarantee suitable behavior. We test the procedure, called HEMQ, on several databases: multi-dimensional Gaussian mixtures, Wiener space cubature, Italian wine cultivars and the MNIST image database. The results indicate that the HEMQ algorithm is robust and versatile and, for the class of Huber-energy kernels, it matches the expected intuitive behavior. ; non ; non ; recherche ; International |
| Τύπος εγγράφου: | report |
| Περιγραφή αρχείου: | application/pdf |
| Γλώσσα: | English |
| Relation: | Cahier de recherche CEREMADE, Université Paris Dauphine-PSL; https://basepub.dauphine.psl.eu/handle/123456789/24103; 46; 2022 |
| Διαθεσιμότητα: | https://basepub.dauphine.psl.eu/handle/123456789/24103 |
| Αριθμός Καταχώρησης: | edsbas.ED91F706 |
| Βάση Δεδομένων: | BASE |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://basepub.dauphine.psl.eu/handle/123456789/24103# Name: EDS - BASE (ns324271) Category: fullText Text: View record from BASE |
|---|---|
| Header | DbId: edsbas DbLabel: BASE An: edsbas.ED91F706 RelevancyScore: 844 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 844.480346679688 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Huber-energy measure quantization – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Turinici%2C+Gabriel%22">Turinici, Gabriel</searchLink> – Name: Publisher Label: Publisher Information Group: PubInfo Data: Paris – Name: DatePubCY Label: Publication Year Group: Date Data: 2023 – Name: Subset Label: Collection Group: HoldingsInfo Data: Base Institutionnelle de Recherche de l'université Paris-Dauphine (BIRD) – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22kernel+quantization%22">kernel quantization</searchLink><br /><searchLink fieldCode="DE" term="%22vector+quantization%22">vector quantization</searchLink><br /><searchLink fieldCode="DE" term="%22machine+learning%22">machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22database+compression%22">database compression</searchLink><br /><searchLink fieldCode="DE" term="%22Analyse%22">Analyse</searchLink> – Name: Subject Label: Time Group: Su Data: 519 – Name: Abstract Label: Description Group: Ab Data: We describe a measure quantization procedure i.e., an algorithm which finds the best approximation of a target probability law (and more generally signed finite variation measure) by a sum of Q Dirac masses (Q being the quantization parameter). The procedure is implemented by minimizing the statistical distance between the original measure and its quantized version; the distance is built from a negative definite kernel and, if necessary, can be computed on the fly and feed to a stochastic optimization algorithm (such as SGD, Adam, .). We investigate theoretically the fundamental questions of existence of the optimal measure quantizer and identify what are the required kernel properties that guarantee suitable behavior. We test the procedure, called HEMQ, on several databases: multi-dimensional Gaussian mixtures, Wiener space cubature, Italian wine cultivars and the MNIST image database. The results indicate that the HEMQ algorithm is robust and versatile and, for the class of Huber-energy kernels, it matches the expected intuitive behavior. ; non ; non ; recherche ; International – Name: TypeDocument Label: Document Type Group: TypDoc Data: report – Name: Format Label: File Description Group: SrcInfo Data: application/pdf – Name: Language Label: Language Group: Lang Data: English – Name: NoteTitleSource Label: Relation Group: SrcInfo Data: Cahier de recherche CEREMADE, Université Paris Dauphine-PSL; https://basepub.dauphine.psl.eu/handle/123456789/24103; 46; 2022 – Name: URL Label: Availability Group: URL Data: https://basepub.dauphine.psl.eu/handle/123456789/24103 – Name: AN Label: Accession Number Group: ID Data: edsbas.ED91F706 |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.ED91F706 |
| RecordInfo | BibRecord: BibEntity: Languages: – Text: English Subjects: – SubjectFull: kernel quantization Type: general – SubjectFull: vector quantization Type: general – SubjectFull: machine learning Type: general – SubjectFull: database compression Type: general – SubjectFull: Analyse Type: general Titles: – TitleFull: Huber-energy measure quantization Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Turinici, Gabriel IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Type: published Y: 2023 Identifiers: – Type: issn-locals Value: edsbas |
| ResultId | 1 |