%0 Generic %1 halko2010algorithm %A Halko, Nathan %A Martinsson, Per-Gunnar %A Shkolnisky, Yoel %A Tygert, Mark %D 2010 %K PCA computation linear_algebra randomized_algorithm %T An algorithm for the principal component analysis of large data sets %U http://arxiv.org/abs/1007.5510 %X Recently popularized randomized methods for principal component analysis (PCA) efficiently and reliably produce nearly optimal accuracy --- even on parallel processors --- unlike the classical (deterministic) alternatives. We adapt one of these randomized methods for use with data sets that are too large to be stored in random-access memory (RAM). (The traditional terminology is that our procedure works efficiently öut-of-core.") We illustrate the performance of the algorithm via several numerical examples. For example, we report on the PCA of a data set stored on disk that is so large that less than a hundredth of it can fit in our computer's RAM.

@misc{halko2010algorithm, abstract = {Recently popularized randomized methods for principal component analysis (PCA) efficiently and reliably produce nearly optimal accuracy --- even on parallel processors --- unlike the classical (deterministic) alternatives. We adapt one of these randomized methods for use with data sets that are too large to be stored in random-access memory (RAM). (The traditional terminology is that our procedure works efficiently "out-of-core.") We illustrate the performance of the algorithm via several numerical examples. For example, we report on the PCA of a data set stored on disk that is so large that less than a hundredth of it can fit in our computer's RAM.}, added-at = {2014-02-03T18:36:40.000+0100}, author = {Halko, Nathan and Martinsson, Per-Gunnar and Shkolnisky, Yoel and Tygert, Mark}, biburl = {https://www.bibsonomy.org/bibtex/271da4f155b0f831ddd18383e0c87abf1/peter.ralph}, interhash = {c21d8cf601e98e6ec01c621b51f6b16c}, intrahash = {71da4f155b0f831ddd18383e0c87abf1}, keywords = {PCA computation linear_algebra randomized_algorithm}, note = {cite arxiv:1007.5510Comment: 17 pages, 3 figures (each with 2 or 3 subfigures), 2 tables (each with 2 subtables)}, timestamp = {2014-02-03T18:36:40.000+0100}, title = {An algorithm for the principal component analysis of large data sets}, url = {http://arxiv.org/abs/1007.5510}, year = 2010 }