Skip to yearly menu bar Skip to main content


Workshop

Uncertainty Estimation via Stochastic Batch Normalization

Andrei Atanov · Arsenii Ashukha · Dmitry Molchanov · Kirill Neklyudov · Dmitry P. Vetrov

East Meeting Level 8 + 15 #12

Tue 1 May, 11 a.m. PDT

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.

Live content is unavailable. Log in and register to view live content