English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Robust Principal Component Analysis as a Nonlinear Eigenproblem

Podosinnikova, A. (2013). Robust Principal Component Analysis as a Nonlinear Eigenproblem. Master Thesis, Universität des Saarlandes, Saarbrücken.

Item is

Files

show Files
hide Files
:
2013_Podosinnikova_MSc Thesis.pdf (Any fulltext), 953KB
 
File Permalink:
-
Name:
2013_Podosinnikova_MSc Thesis.pdf
Description:
-
OA-Status:
Visibility:
Restricted (Max Planck Institute for Informatics, MSIN; )
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Podosinnikova, Anastasia1, Author           
Hein, Matthias2, Advisor
Gemulla, Rainer3, Referee           
Affiliations:
1International Max Planck Research School, MPI for Informatics, Max Planck Society, ou_1116551              
2External Organizations, ou_persistent22              
3Databases and Information Systems, MPI for Informatics, Max Planck Society, ou_24018              

Content

show
hide
Free keywords: -
 Abstract: Principal Component Analysis (PCA) is a widely used tool for, e.g., exploratory data analysis, dimensionality reduction and clustering. However, it is well known that PCA is strongly aected by the presence of outliers and, thus, is vulnerable to both gross measurement error and adversarial manipulation of the data. This phenomenon motivates the development of robust PCA as the problem of recovering the principal components of the uncontaminated data. In this thesis, we propose two new algorithms, QRPCA and MDRPCA, for robust PCA components based on the projection-pursuit approach of Huber. While the resulting optimization problems are non-convex and non-smooth, we show that they can be eciently minimized via the RatioDCA using bundle methods/accelerated proximal methods for the interior problem. The key ingredient for the most promising algorithm (QRPCA) is a robust, location invariant scale measure with breakdown point 0.5. Extensive experiments show that our QRPCA is competitive with current state-of-the-art methods and outperforms other methods in particular for a large number of outliers.

Details

show
hide
Language(s): eng - English
 Dates: 2013-072013
 Publication Status: Issued
 Pages: -
 Publishing info: Saarbrücken : Universität des Saarlandes
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Podosinnikova2013
 Degree: Master

Event

show

Legal Case

show

Project information

show

Source

show