Skip to Main content Skip to Navigation
Journal articles

Probabilistic learning on manifolds

Abstract : This paper presents novel mathematical results in support of the probabilistic learning on manifolds (PLoM) recently introduced by the authors. An initial dataset, constituted of a small number of points given in an Euclidean space, is given. The points are independent realizations of a vector-valued random variable for which its non-Gaussian probability measure is unknown but is, a priori, concentrated in an unknown subset of the Euclidean space. A learned dataset, constituted of additional realizations, is constructed. A transport of the probability measure estimated with the initial dataset is done through a linear transformation constructed using a reduced-order diffusion-maps basis. It is proven that this transported measure is a marginal distribution of the invariant measure of a reduced-order Itô stochastic differential equation. The concentration of the probability measure is preserved. This property is shown by analyzing a distance between the random matrix constructed with the PLoM and the matrix representing the initial dataset, as a function of the dimension of the basis. It is further proven that this distance has a minimum for a dimension of the reduced-order diffusion-maps basis that is strictly smaller than the number of points in the initial dataset.
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download

https://hal-upec-upem.archives-ouvertes.fr/hal-02919127
Contributor : Christian Soize <>
Submitted on : Friday, August 21, 2020 - 4:07:36 PM
Last modification on : Tuesday, September 29, 2020 - 2:38:35 PM

File

publi-2020-FoDS-1-29-soize-gha...
Files produced by the author(s)

Identifiers

Collections

Citation

Christian Soize, Roger Ghanem. Probabilistic learning on manifolds. Foundations of Data Science, American Institute of Mathematical Sciences, 2020, online, 21 August 2020, pp.1-29. ⟨10.3934/fods.2020013⟩. ⟨hal-02919127⟩

Share

Metrics

Record views

16

Files downloads

19