Skip to yearly menu bar Skip to main content


Poster

Nonparametric Indirect Active Learning

Shashank Singh

Auditorium 1 Foyer 33

Abstract:

Typical models of active learning assume a learner can directly manipulate or query a covariate X to study its relationship with a response Y. However, if X is a feature of a complex system, it may be possible only to indirectly influence X by manipulating a control variable Z, a scenario we refer to as Indirect Active Learning. Under a nonparametric fixed-budget model of Indirect Active Learning, we study minimax convergence rates for estimating a local relationship between X and Y, with different rates depending on the complexities and noise levels of the relationships between Z and X and between X and Y. We also derive minimax rates for passive learning under comparable assumptions, finding in many cases that, while there is an asymptotic benefit to active learning, this benefit is fully realized by a simple two-stage learner that runs two passive experiments in sequence. Experiments with simulated data validate our theoretical results.

Live content is unavailable. Log in and register to view live content