Random projection in dimensionality reduction: applications to image and text data Export

@inproceedings{citeulike:416422, abstract = {Random projections have recently emerged as a powerful method for dimensionality reduction. Theoretical results indicate that the method preserves distances quite nicely; however, empirical results are sparse. We present experimental results on using random projection as a dimensionality reduction tool in a number of cases, where the high dimensionality of the data would otherwise lead to burden-some computations. Our application areas are the processing of both noisy and noiseless images, and information retrieval in text documents. We show that projecting the data onto a random lower-dimensional subspace yields results comparable to conventional dimensionality reduction methods such as principal component analysis: the similarity of data vectors is preserved well under random projection. However, using random projections is computationally significantly less expensive than using, e.g., principal component analysis. We also show experimentally that using a sparse random matrix gives additional computational savings in random projection.}, address = {New York, NY, USA}, author = {Bingham, Ella and Mannila, Heikki}, booktitle = {KDD '01: Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining}, citeulike-article-id = {416422}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=502546}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/502512.502546}, doi = {10.1145/502512.502546}, isbn = {158113391X}, keywords = {applied-mathematics}, pages = {245--250}, posted-at = {2006-02-01 03:06:34}, priority = {2}, publisher = {ACM Press}, title = {Random projection in dimensionality reduction: applications to image and text data}, url = {http://dx.doi.org/10.1145/502512.502546}, year = {2001} }

TY - CONF ID - citeulike:416422 L3 - citeulike-article-id:416422 N2 - Random projections have recently emerged as a powerful method for dimensionality reduction. Theoretical results indicate that the method preserves distances quite nicely; however, empirical results are sparse. We present experimental results on using random projection as a dimensionality reduction tool in a number of cases, where the high dimensionality of the data would otherwise lead to burden-some computations. Our application areas are the processing of both noisy and noiseless images, and information retrieval in text documents. We show that projecting the data onto a random lower-dimensional subspace yields results comparable to conventional dimensionality reduction methods such as principal component analysis: the similarity of data vectors is preserved well under random projection. However, using random projections is computationally significantly less expensive than using, e.g., principal component analysis. We also show experimentally that using a sparse random matrix gives additional computational savings in random projection. SN - 158113391X AD - New York, NY, USA EP - 250 TI - Random projection in dimensionality reduction: applications to image and text data PB - ACM Press T2 - KDD '01: Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining SP - 245 KW - applied-mathematics AU - Bingham, Ella AU - Mannila, Heikki PY - 2001/// UR - http://dx.doi.org/10.1145/502512.502546 ER -