Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Widening the scope of an eigenvector stochastic approximation process and application to streaming PCA and related methods

Abstract : We prove the almost sure convergence of Oja-type processes to eigenvectors of the expectation B of a random matrix while relaxing the i.i.d. assumption on the observed random matrices (B n) and assuming either (B n) converges to B or (E[B n |T n ]) converges to B where T n is the sigma-field generated by the events before time n. As an application of this generalization, the online PCA of a random vector Z can be performed when there is a data stream of i.i.d. observations of Z, even when both the metric M used and the expectation of Z are unknown and estimated online. Moreover, in order to update the stochastic approximation process at each step, we are no longer bound to using only a mini-batch of observations of Z, but all previous observations up to the current step can be used without having to store them. This is useful not only when dealing with streaming data but also with Big Data as one can process the latter sequentially as a data stream. In addition the general framework of this process, unlike other algorithms in the literature, also covers the case of factorial methods related to PCA.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.inria.fr/hal-03038206
Contributor : Jean-Marie Monnez <>
Submitted on : Thursday, December 3, 2020 - 12:52:06 PM
Last modification on : Thursday, January 21, 2021 - 1:48:04 PM

File

article_monnez_skiredj_2020111...
Files produced by the author(s)

Identifiers

Citation

Jean-Marie Monnez, Abderrahman Skiredj. Widening the scope of an eigenvector stochastic approximation process and application to streaming PCA and related methods. 2020. ⟨hal-03038206⟩

Share

Metrics

Record views

61

Files downloads

64