Neural Information Processing Systems http://nips.cc/

We mitigate the usual worst-case nature of minimax analysis by showing that our bounds are tight for any given31 hypothesis class, and, tight in any noise regime (Theorems 1 and 2).

Ensemble approaches for uncertainty estimation have recently been applied to the tasks of misclassification detection, out-of-distribution input detection and adversarial attack detection. Prior Networks have been proposed as an approach to efficiently emulate an ensemble of models for classification by parameteris-ing a Dirichlet prior distribution over output distributions.

However, we make no serious efforts to find the optimal architecture. In fact, we use the same 13 architecture for allour experiments, across the scales. Webelievethe performance onaparticular task can be further improved by carefully curating the neural architecture.