Fully Understanding the Hashing Trick

arXiv1805.08539MaRDI QIDQ6301936FDOQ6301936

Authors: Casper Benjamin Freksen, Lior Kamma, Kasper Green Larsen 

Publication date: 22 May 2018

Abstract: Feature hashing, also known as {em the hashing trick}, introduced by Weinberger et al. (2009), is one of the key techniques used in scaling-up machine learning algorithms. Loosely speaking, feature hashing uses a random sparse projection matrix $A:mathbb{R}^{n}omathbb{R}^m$ (where $mlln$) in order to reduce the dimension of the data from $n$ to $m$ while approximately preserving the Euclidean norm. Every column of $A$ contains exactly one non-zero entry, equals to either $-1$ or $1$. Weinberger et al. showed tail bounds on $|Ax{|}_2^2$. Specifically they showed that for every $varepsilon,delta$, if $|x{|}_{infty}/|x{|}_2$ is sufficiently small, and $m$ is sufficiently large, then ${\displaystyle }$Pr[ ; | ;|Ax|_2^2 - |x|_2^2; | < varepsilon |x|_2^2 ;] ge 1 - delta ;.${\displaystyle }$ These bounds were later extended by Dasgupta etal (2010) and most recently refined by Dahlgaard et al. (2017), however, the true nature of the performance of this key technique, and specifically the correct tradeoff between the pivotal parameters $|x{|}_{infty}/|x{|}_2,m,varepsilon,delta$ remained an open question. We settle this question by giving tight asymptotic bounds on the exact tradeoff between the central parameters, thus providing a complete understanding of the performance of feature hashing. We complement the asymptotic bound with empirical data, which shows that the constants "hiding" in the asymptotic notation are, in fact, very close to $1$, thus further illustrating the tightness of the presented bounds in practice.

This page was built for publication: Fully Understanding the Hashing Trick

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6301936)