Poster

Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations

Winnie Xu · Ricky T. Q. Chen · Xuechen Li · David Duvenaud

Virtual
[ Abstract ]
[ Visit Poster at Spot A0 in Virtual World ] [ Slides
Mon 28 Mar 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

We perform scalable approximate inference in continuous-depth Bayesian neural networks. In this model class, uncertainty about separate weights in each layer gives hidden units that follow a stochastic differential equation. We demonstrate gradient-based stochastic variational inference in this infinite-parameter setting, producing arbitrarily-flexible approximate posteriors. We also derive a novel gradient estimator that approaches zero variance as the approximate posterior over weights approaches the true posterior. This approach brings continuous-depth Bayesian neural nets to a competitive comparison against discrete-depth alternatives, while inheriting the memory-efficient training and tunable precision of Neural ODEs.

Chat is not available.