Back to results

Massachusetts Institute of Technology

Learning with matrix factorizations

Abstract

dc:description.abstract

Matrices that can be factored into a product of two simpler matrices can serve as a useful and often natural model in the analysis of tabulated or high-dimensional data. Models based on matrix factorization (Factor Analysis, PCA) have been extensively used in statistical analysis and machine learning for over a century, with many new formulations and models suggested in recent years (Latent Semantic Indexing, Aspect Models, Probabilistic PCA, Exponential PCA, Non-Negative Matrix Factorization and others). In this thesis we address several issues related to learning with matrix factorizations: we study the asymptotic behavior and generalization ability of existing methods, suggest new optimization methods, and present a novel maximum-margin high-dimensional matrix factorization formulation.

Degree

thesis:*
Department dc:contributor.department
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Grantor dc:publisher
Massachusetts Institute of Technology
Year dc:date.issued
2004

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Srebro, Nathan, 1974-
Advisor dc:contributor.advisor
  • Tommi S. Jaakkola.

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1721.1/28743
OAI identifier oai:identifier
oai:dspace.mit.edu:1721.1/28743

Chain of custody

source
Harvested from
MIT
Base URL
dspace.mit.edu/oai/request
Last updated
2026-07-22
Source record
OAI-PMH GetRecord
citation

Srebro, Nathan, 1974-. Learning with matrix factorizations. Massachusetts Institute of Technology, 2004. http://hdl.handle.net/1721.1/28743