Active Learning with Safety ConstraintsDownload PDF

Published: 31 Oct 2022, Last Modified: 13 Oct 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: bandits, linear bandits, active classification, active learning
Abstract: Active learning methods have shown great promise in reducing the number of samples necessary for learning. As automated learning systems are adopted into real-time, real-world decision-making pipelines, it is increasingly important that such algorithms are designed with safety in mind. In this work we investigate the complexity of learning the best safe decision in interactive environments. We reduce this problem to a safe linear bandits problem, where our goal is to find the best arm satisfying certain (unknown) safety constraints. We propose an adaptive experimental design-based algorithm, which we show efficiently trades off between the difficulty of showing an arm is unsafe vs suboptimal. To our knowledge, our results are the first on best-arm identification in linear bandits with safety constraints. In practice, we demonstrate that this approach performs well on synthetic and real world datasets.
TL;DR: We consider the problem of best-arm identification under safety constraints.
Supplementary Material: pdf
12 Replies