Active Learning Polynomial Threshold Functions

01/24/2022
by   Omri Ben-Eliezer, et al.
0

We initiate the study of active learning polynomial threshold functions (PTFs). While traditional lower bounds imply that even univariate quadratics cannot be non-trivially actively learned, we show that allowing the learner basic access to the derivatives of the underlying classifier circumvents this issue and leads to a computationally efficient algorithm for active learning degree-d univariate PTFs in Õ(d^3log(1/εδ)) queries. We also provide near-optimal algorithms and analyses for active learning PTFs in several average case settings. Finally, we prove that access to derivatives is insufficient for active learning multivariate PTFs, even those of just two variables.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset