Fast and faster: a comparison of two streamed matrix decomposition algorithms
From Brede Wiki
Conference paper (help) | |
---|---|
Fast and faster: a comparison of two streamed matrix decomposition algorithms | |
Authors: | Radim Řehůřek |
Citation: | NIPS Workshop on Low-Rank Methods for Large-Scale Machine Learning : 2010 |
Editors: | |
Publisher: | Define publisher |
Meeting: | NIPS Workshop on Low-Rank Methods for Large-Scale Machine Learning |
Database(s): | |
DOI: | Define doi. |
Link(s): | http://arxiv.org/pdf/1102.5597v1 |
Search | |
Web: | DuckDuckGo Bing Google Yahoo! — Google PDF |
Article: | Google Scholar PubMed |
Restricted: | DTU Digital Library |
Services | |
Format: | BibTeX |
Fast and faster: a comparison of two streamed matrix decomposition algorithms describes a matrix decomposition algorithm.
To test the developed algorithm the used a matrix with the size 100'000 x 3'199'665 constructed from the English Wikipedia as a term-document matrix, i.e., latent semantic indexing.
The algorithm is associated with the Gensim vector space modeling software implement in the Python programming language.