1

Conjugate Energy-Based Models

We propose conjugate energy-based models (EBMs), a class of deep latent-variable models with a tractable posterior. Conjugate EBMs have similar use cases as variational autoencoders, in the sense that they learn an unsupervised mapping between data …

Nested Variational Inference

We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an inclusive or exclusive KL divergence at each level of nesting. NVI is applicable to many commonly-used importance …

Rate-Regularization and Generalization in VAEs

Variational autoencoders (VAEs) optimize an objective that comprises a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information, which is often interpreted as a regularizer that controls the …

Can VAEs Generate Novel Examples?

An implicit goal in works on deep generative models is that such models should be able to generate novel examples that were not previously seen in the training data. In this paper, we investigate to what extent this property holds for widely employed …

Structured Disentangled Representations

Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing …

Structured Neural Topic Models for Reviews

We present Variational Aspect-based Latent Topic Allocation (VALTA), a family of autoencoding topic models that learn aspect-based representations of reviews. VALTA defines a user-item encoder that maps bag-of-words vectors for combined reviews …