Self-Reflective Variational Autoencoder

Ifigeneia Apostolopoulou, Elan Rosenfeld, Artur Dubrawski

Keywords: deep generative models, variational inference, approximate inference, variational auto encoder

Abstract: The Variational Autoencoder (VAE) is a powerful framework for learning probabilistic latent variable generative models. However, typical assumptions on the approximate posterior distributions can substantially restrict its capacity for inference and generative modeling. Variational inference based on neural autoregressive models respects the conditional dependencies of the exact posterior, but this flexibility comes at a cost: the resulting models are expensive to train in high-dimensional regimes and can be slow to produce samples. In this work, we introduce an orthogonal solution, which we call self-reflective inference. By redesigning the hierarchical structure of existing VAE architectures, self-reflection ensures that the stochastic flow preserves the factorization of the exact posterior, sequentially updating the latent codes in a manner consistent with the generative model. We empirically demonstrate the advantages of matching the variational posterior to the exact posterior---on binarized MNIST self-reflective inference achieves state-of-the-art performance without resorting to complex, computationally expensive components such as autoregressive layers. Moreover, we design a variational normalizing flow that employs the proposed architecture, yielding predictive benefits compared to its purely generative counterpart. Our proposed modification is quite general and it complements the existing literature; self-reflective inference can naturally leverage advances in distribution estimation and generative modeling to improve the capacity of each layer in the hierarchy.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We present the first deep probabilistic model without modeling mismatches between the true and variational posterior yielding computational and predictive benefits.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=tBJwNqPKah