b-Bit Minwise Hashing for Large-Scale Learning

Minwise hashing is a standard technique in the context of search for efficiently computing set similarities. The recent development of b-bit minwise hashing pro-vides a substantial improvement by storing only the lowest b bits of each hashed value. In this paper, we demonstrate that b-bit minwise hashing can be natu-rally integrated with linear learning algorithms such as linear SVM and logistic regression, to solve large-scale and high-dimensional statistical learning tasks, es-pecially when the data do not fit in memory. We compare b-bit minwise hashing with the Count-Min (CM) and Vowpal Wabbit (VW) algorithms, which have es-sentially the same variances as random projections. Our theoretical and empirical comparisons illustrate that b-bit minwise hashing is significantly more accurate (at the same storage cost) than VW (and random projections) for binary data.