Skip to yearly menu bar Skip to main content


Poster

Hybrid Models with Deep and Invertible Features

Eric Nalisnick · Akihiro Matsukawa · Yee-Whye Teh · Dilan Gorur · Balaji Lakshminarayanan

Pacific Ballroom #268

Keywords: [ Bayesian Deep Learning ] [ Deep Generative Models ]


Abstract:

We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive property of our model is that both p(features), the density of the features, and p(targets|features), the predictive distribution, can be computed exactly in a single feed-forward pass. We show that our hybrid model, despite the invertibility constraints, achieves similar accuracy to purely predictive models. Yet the generative component remains a good model of the input features despite the hybrid optimization objective. This offers additional capabilities such as detection of out-of-distribution inputs and enabling semi-supervised learning. The availability of the exact joint density p(targets, features) also allows us to compute many quantities readily, making our hybrid model a useful building block for downstream applications of probabilistic deep learning.

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