PublicationsPrevious | item20 | NextFrom: Art Owen owen@stat.Stanford.EDU Date: Mon, 24 Jan 2000 10:49:37 -0800 (PST) Subject: New paper on data squashing The paper is at the top of http://www-stat.stanford.edu/~owen/reports The idea in data squashing is to scale down a data set to existing algorithms, instead of scaling up algorithms to large data sets. Data squashing originated at ATT. The present paper: 1) compares data squashing to other methods from sampling, numerical integration, and nonparametric likelihood 2) tries squashing with boosted trees as well as logistic regression 3) investigates accuracy of classifications, in addition to accuracy of coefficients -Art Owen Previous | item20 | Next |
Copyright © 2000 KDnuggets. Subscribe to KDnuggets News!