Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling
| hal.structure.identifier | Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio [PANAMA] | |
| hal.structure.identifier | Dynamic Networks : Temporal and Structural Capture Approach [DANTE] | |
| dc.contributor.author | GRIBONVAL, Rémi | |
| hal.structure.identifier | Laboratoire de Mathématiques d'Orsay [LMO] | |
| hal.structure.identifier | Understanding the Shape of Data [DATASHAPE] | |
| dc.contributor.author | BLANCHARD, Gilles | |
| hal.structure.identifier | GIPSA Pôle Géométrie, Apprentissage, Information et Algorithmes [GIPSA-GAIA] | |
| dc.contributor.author | KERIVEN, Nicolas | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | TRAONMILIN, Yann | |
| dc.date.accessioned | 2024-04-04T02:45:59Z | |
| dc.date.available | 2024-04-04T02:45:59Z | |
| dc.date.issued | 2021-08-21 | |
| dc.identifier.issn | 2520-2316 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/191510 | |
| dc.description.abstractEn | We provide statistical learning guarantees for two unsupervised learning tasks in the context of compressive statistical learning, a general framework for resource-efficient large-scale learning that we introduced in a companion paper.The principle of compressive statistical learning is to compress a training collection, in one pass, into a low-dimensional sketch (a vector of random empirical generalized moments) that captures the information relevant to the considered learning task. We explicitly describe and analyze random feature functions which empirical averages preserve the needed information for compressive clustering and compressive Gaussian mixture modeling with fixed known variance, and establish sufficient sketch sizes given the problem dimensions. | |
| dc.description.sponsorship | Approches statistiquement et computationnellement efficicaces pour l'intelligence artificielle - ANR-19-CHIA-0021 | |
| dc.description.sponsorship | Algorithmes, Approximations, Parcimonie et Plongements pour l'IA - ANR-19-CHIA-0009 | |
| dc.language.iso | en | |
| dc.publisher | EMS Publishing House | |
| dc.subject.en | random moments | |
| dc.subject.en | random features | |
| dc.subject.en | clustering | |
| dc.subject.en | mixture modeling | |
| dc.subject.en | principal component analysis. | |
| dc.subject.en | principal component analysis | |
| dc.subject.en | dimension reduction | |
| dc.subject.en | unsupervised learning | |
| dc.subject.en | kernel mean embedding | |
| dc.subject.en | statistical learning | |
| dc.title.en | Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling | |
| dc.type | Article de revue | |
| dc.identifier.doi | 10.4171/msl/21 | |
| dc.subject.hal | Mathématiques [math]/Statistiques [math.ST] | |
| dc.subject.hal | Informatique [cs]/Théorie de l'information [cs.IT] | |
| dc.subject.hal | Informatique [cs]/Apprentissage [cs.LG] | |
| dc.identifier.arxiv | 2004.08085 | |
| dc.description.sponsorshipEurope | PLEASE: Projections, Learning, and Sparsity for Efficient data-processing | |
| bordeaux.journal | Mathematical Statistics and Learning | |
| bordeaux.page | 165–257 | |
| bordeaux.volume | 3 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.issue | 2 | |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-02536818 | |
| hal.version | 1 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-02536818v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Mathematical%20Statistics%20and%20Learning&rft.date=2021-08-21&rft.volume=3&rft.issue=2&rft.spage=165%E2%80%93257&rft.epage=165%E2%80%93257&rft.eissn=2520-2316&rft.issn=2520-2316&rft.au=GRIBONVAL,%20R%C3%A9mi&BLANCHARD,%20Gilles&KERIVEN,%20Nicolas&TRAONMILIN,%20Yann&rft.genre=article |
Files in this item
| Files | Size | Format | View |
|---|---|---|---|
|
There are no files associated with this item. |
|||