Hybrid Models with Deep and Invertible Features

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. Moreover 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.

ICML 2019

Cited by in corpus (5)

• Contrastive Training for Improved Out-of-Distribution Detection
• Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
• InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers
• Ordering Dimensions with Nested Dropout Normalizing Flows
• Learning the Prediction Distribution for Semi-Supervised Learning with Normalising Flows