CUED Publications database

Robustness of Bayesian pool-based active learning against prior misspecification

Cuong, NV and Ye, N and Lee, WS (2016) Robustness of Bayesian pool-based active learning against prior misspecification. In: UNSPECIFIED pp. 1512-1518..

Full text not available from this repository.

Abstract

© 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. We study the robustness of active learning (AL) algorithms against prior misspecification: whether an algorithm achieves similar performance using a perturbed prior as compared to using the true prior. In both the average and worst cases of the maximum coverage setting, we prove that all α-approximate algorithms are robust (i.e., near α-approximate) if the utility is Lipschitz continuous in the prior. We further show that robustness may not be achieved if the utility is non-Lipschitz. This suggests we should use a Lipschitz utility for AL if robustness is required. For the minimum cost setting, we can also obtain a robustness result for approximate AL algorithms. Our results imply that many commonly used AL algorithms are robust against perturbed priors. We then propose the use of a mixture prior to alleviate the problem of prior misspecification. We analyze the robustness of the uniform mixture prior and show experimentally that it performs reasonably well in practice.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:19
Last Modified: 07 Sep 2017 01:47
DOI: