Matches in SemOpenAlex for { <https://semopenalex.org/work/W2206687718> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2206687718 abstract "This thesis focuses on obtaining generalization bounds for random samples in reproducing kernel Hilbert spaces. The approach consists in first obtaining non-asymptotic dimension-free bounds in finite-dimensional spaces using some PAC-Bayesian inequalities related to Gaussian perturbations and then in generalizing the results in a separable Hilbert space. We first investigate the question of estimating the Gram operator by a robust estimator from an i. i. d. sample and we present uniform bounds that hold under weak moment assumptions. These results allow us to qualify principal component analysis independently of the dimension of the ambient space and to propose stable versions of it. In the last part of the thesis we present a new algorithm for spectral clustering. It consists in replacing the projection on the eigenvectors associated with the largest eigenvalues of the Laplacian matrix by a power of the normalized Laplacian. This iteration, justified by the analysis of clustering in terms of Markov chains, performs a smooth truncation. We prove nonasymptotic bounds for the convergence of our spectral clustering algorithm applied to a random sample of points in a Hilbert space that are deduced from the bounds for the Gram operator in a Hilbert space. Experiments are done in the context of image analysis." @default.
- W2206687718 created "2016-06-24" @default.
- W2206687718 creator A5040739485 @default.
- W2206687718 date "2015-09-24" @default.
- W2206687718 modified "2023-09-24" @default.
- W2206687718 title "Generalization bounds for random samples in Hilbert spaces" @default.
- W2206687718 hasPublicationYear "2015" @default.
- W2206687718 type Work @default.
- W2206687718 sameAs 2206687718 @default.
- W2206687718 citedByCount "2" @default.
- W2206687718 countsByYear W22066877182016 @default.
- W2206687718 countsByYear W22066877182021 @default.
- W2206687718 crossrefType "dissertation" @default.
- W2206687718 hasAuthorship W2206687718A5040739485 @default.
- W2206687718 hasConcept C105611402 @default.
- W2206687718 hasConcept C105795698 @default.
- W2206687718 hasConcept C121332964 @default.
- W2206687718 hasConcept C134306372 @default.
- W2206687718 hasConcept C158693339 @default.
- W2206687718 hasConcept C28826006 @default.
- W2206687718 hasConcept C33923547 @default.
- W2206687718 hasConcept C60064506 @default.
- W2206687718 hasConcept C62520636 @default.
- W2206687718 hasConcept C62799726 @default.
- W2206687718 hasConcept C64812099 @default.
- W2206687718 hasConcept C73555534 @default.
- W2206687718 hasConcept C76103427 @default.
- W2206687718 hasConcept C80884492 @default.
- W2206687718 hasConceptScore W2206687718C105611402 @default.
- W2206687718 hasConceptScore W2206687718C105795698 @default.
- W2206687718 hasConceptScore W2206687718C121332964 @default.
- W2206687718 hasConceptScore W2206687718C134306372 @default.
- W2206687718 hasConceptScore W2206687718C158693339 @default.
- W2206687718 hasConceptScore W2206687718C28826006 @default.
- W2206687718 hasConceptScore W2206687718C33923547 @default.
- W2206687718 hasConceptScore W2206687718C60064506 @default.
- W2206687718 hasConceptScore W2206687718C62520636 @default.
- W2206687718 hasConceptScore W2206687718C62799726 @default.
- W2206687718 hasConceptScore W2206687718C64812099 @default.
- W2206687718 hasConceptScore W2206687718C73555534 @default.
- W2206687718 hasConceptScore W2206687718C76103427 @default.
- W2206687718 hasConceptScore W2206687718C80884492 @default.
- W2206687718 hasLocation W22066877181 @default.
- W2206687718 hasOpenAccess W2206687718 @default.
- W2206687718 hasPrimaryLocation W22066877181 @default.
- W2206687718 hasRelatedWork W1499995586 @default.
- W2206687718 hasRelatedWork W1528907134 @default.
- W2206687718 hasRelatedWork W1652432954 @default.
- W2206687718 hasRelatedWork W1993288992 @default.
- W2206687718 hasRelatedWork W1996652862 @default.
- W2206687718 hasRelatedWork W2014857453 @default.
- W2206687718 hasRelatedWork W2053635157 @default.
- W2206687718 hasRelatedWork W2083999542 @default.
- W2206687718 hasRelatedWork W2101095277 @default.
- W2206687718 hasRelatedWork W2112531253 @default.
- W2206687718 hasRelatedWork W2122789001 @default.
- W2206687718 hasRelatedWork W2123818990 @default.
- W2206687718 hasRelatedWork W2159066948 @default.
- W2206687718 hasRelatedWork W2528572894 @default.
- W2206687718 hasRelatedWork W2963829020 @default.
- W2206687718 hasRelatedWork W2963834606 @default.
- W2206687718 hasRelatedWork W3033187330 @default.
- W2206687718 hasRelatedWork W3083789465 @default.
- W2206687718 hasRelatedWork W3208287644 @default.
- W2206687718 hasRelatedWork W946533221 @default.
- W2206687718 isParatext "false" @default.
- W2206687718 isRetracted "false" @default.
- W2206687718 magId "2206687718" @default.
- W2206687718 workType "dissertation" @default.