Revisiting clustering as matrix factorisation on the Stiefel manifold - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Revisiting clustering as matrix factorisation on the Stiefel manifold

Abstract

This paper studies clustering for possibly high dimensional data (e.g. images, time series, gene expression data, and many other settings), and rephrase it as low rank matrix estimation in the PAC-Bayesian framework. Our approach leverages the well known Burer-Monteiro factorisation strategy from large scale optimisation, in the context of low rank estimation. Moreover, our Burer-Monteiro factors are shown to lie on a Stiefel manifold. We propose a new generalized Bayesian estimator for this problem and prove novel prediction bounds for clustering. We also devise a componentwise Langevin sampler on the Stiefel manifold to compute this estimator.
Fichier principal
Vignette du fichier
main.pdf (280.39 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02064396 , version 1 (11-03-2019)

Identifiers

Cite

Stephane Chretien, Benjamin Guedj. Revisiting clustering as matrix factorisation on the Stiefel manifold. LOD 2020 - the Sixth International Conference on Machine Learning, Optimisation and Data Science, Jul 2020, Siena, Italy. ⟨hal-02064396⟩
56 View
293 Download

Altmetric

Share

Gmail Facebook X LinkedIn More