Show simple item record

Learning with Matrix Factorizations

dc.date.accessioned2005-12-22T02:16:24Z
dc.date.accessioned2018-11-24T10:24:19Z
dc.date.available2005-12-22T02:16:24Z
dc.date.available2018-11-24T10:24:19Z
dc.date.issued2004-11-22
dc.identifier.urihttp://hdl.handle.net/1721.1/30507
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/30507
dc.description.abstractMatrices that can be factored into a product of two simpler matricescan serve as a useful and often natural model in the analysis oftabulated or high-dimensional data. Models based on matrixfactorization (Factor Analysis, PCA) have been extensively used instatistical analysis and machine learning for over a century, withmany new formulations and models suggested in recent years (LatentSemantic Indexing, Aspect Models, Probabilistic PCA, Exponential PCA,Non-Negative Matrix Factorization and others). In this thesis weaddress several issues related to learning with matrix factorizations:we study the asymptotic behavior and generalization ability ofexisting methods, suggest new optimization methods, and present anovel maximum-margin high-dimensional matrix factorizationformulation.
dc.format.extent132 p.
dc.format.extent96239481 bytes
dc.format.extent5561927 bytes
dc.language.isoen_US
dc.subjectAI
dc.titleLearning with Matrix Factorizations


Files in this item

FilesSizeFormatView
MIT-CSAIL-TR-2004-076.pdf5.561Mbapplication/pdfView/Open
MIT-CSAIL-TR-2004-076.ps96.23Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record