Timezone: »

 
Poster
PAC Prediction Sets for Meta-Learning
Sangdon Park · Edgar Dobriban · Insup Lee · Osbert Bastani

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #103
in Poster Session 6 »

Uncertainty quantification is a key component of machine learning models targeted at safety-critical systems such as in healthcare or autonomous vehicles. We study this problem in the context of meta learning, where the goal is to quickly adapt a predictor to new tasks. In particular, we propose a novel algorithm to construct \emph{PAC prediction sets}, which capture uncertainty via sets of labels, that can be adapted to new tasks with only a few training examples. These prediction sets satisfy an extension of the typical PAC guarantee to the meta learning setting; in particular, the PAC guarantee holds with high probability over future tasks. We demonstrate the efficacy of our approach on four datasets across three application domains: mini-ImageNet and CIFAR10-C in the visual domain, FewRel in the language domain, and the CDC Heart Dataset in the medical domain. In particular, our prediction sets satisfy the PAC guarantee while having smaller size compared to other baselines that also satisfy this guarantee.

Keywords: Few-Shot Learning · uncertainty quantification · meta learning · conformal prediction · prediction sets · probably approximately correct
[ Paper]  [ Slides]  [ Poster]  [ OpenReview] 

Author Information

Sangdon Park (Georgia Institute of Technology)
Edgar Dobriban (University of Pennsylvania)
Insup Lee (University of Pennsylvania)
Osbert Bastani (University of Pennsylvania)

More from the Same Authors