EconPapers    
Economics at your fingertips  
 

Denise: Deep Learning based Robust PCA for Positive Semidefinite Matrices

Calypso Herrera, Florian Krach, Anastasis Kratsios, Pierre Ruyssen and Josef Teichmann

Papers from arXiv.org

Abstract: The robust PCA of high-dimensional matrices plays an essential role when isolating key explanatory features. The currently available methods for performing such a low-rank plus sparse decomposition are matrix specific, meaning, the algorithm must re-run each time a new matrix should be decomposed. Since these algorithms are computationally expensive, it is preferable to learn and store a function that instantaneously performs this decomposition when evaluated. Therefore, we introduce Denise, a deep learning-based algorithm for robust PCA of symmetric positive semidefinite matrices, which learns precisely such a function. Theoretical guarantees that Denise's architecture can approximate the decomposition function, to arbitrary precision and with arbitrarily high probability, are obtained. The training scheme is also shown to convergence to a stationary point of the robust PCA's loss-function. We train Denise on a randomly generated dataset, and evaluate the performance of the DNN on synthetic and real-world covariance matrices. Denise achieves comparable results to several state-of-the-art algorithms in terms of decomposition quality, but as only one evaluation of the learned DNN is needed, Denise outperforms all existing algorithms in terms of computation time.

Date: 2020-04, Revised 2020-06
New Economics Papers: this item is included in nep-big and nep-cmp
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed

Downloads: (external link)
http://arxiv.org/pdf/2004.13612 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2004.13612

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().

 
Page updated 2020-06-13
Handle: RePEc:arx:papers:2004.13612