Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Uncertainty Estimation via Stochastic Batch Normalization
Andrei Atanov, Arsenii Ashukha, Dmitry Molchanov, Kirill Neklyudov, Dmitry Vetrov
Feb 12, 2018 (modified: Feb 12, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation. We propose a probabilistic model and show that Batch Normalization maximazes the lower bound of its marginalized log-likelihood. Then, according to the new probabilistic model, we design an algorithm which acts consistently during train and test. However, inference becomes computationally inefficient. To reduce memory and computational cost, we propose Stochastic Batch Normalization -- an efficient approximation of proper inference procedure. This method provides us with a scalable uncertainty estimation technique. We demonstrate the performance of Stochastic Batch Normalization on popular architectures (including deep convolutional architectures: VGG-like and ResNets) for MNIST and CIFAR-10 datasets.
TL;DR:We propose a probabilistic view on Batch Normalization and an efficient test-time averaging technique for uncertainty estimation in batch-normalized DNNs.
Keywords:Batch Normalization, Uncertainty Estimation, Deep Neural Networks
Enter your feedback below and we'll get back to you as soon as possible.