Constants Matter: The Performance Gains of Active Learning

Stephen Mussmann · Sanjoy Dasgupta

Ballroom 3 & 4
[ Abstract ] [ Livestream: Visit Theory ]
Wed 20 Jul 11:35 a.m. — 11:40 a.m. PDT
[ Slides [ Paper PDF

Within machine learning, active learning studies the gains in performance made possible by adaptively selecting data points to label. In this work, we show through upper and lower bounds, that for a simple benign setting of well-specified logistic regression on a uniform distribution over a sphere, the expected excess error of both active learning and random sampling have the same inverse proportional dependence on the number of samples. Importantly, due to the nature of lower bounds, any more general setting does not allow a better dependence on the number of samples. Additionally, we show a variant of uncertainty sampling can achieve a faster rate of convergence than random sampling by a factor of the Bayes error, a recent empirical observation made by other work. Qualitatively, this work is pessimistic with respect to the asymptotic dependence on the number of samples, but optimistic with respect to finding performance gains in the constants.

Chat is not available.