LGAIMLSep 21, 2022

Continuous Mixtures of Tractable Probabilistic Models

arXiv:2209.10584v326 citationsh-index: 25
Originality Highly original
AI Analysis

This work addresses the problem of improving tractable probabilistic inference for researchers and practitioners in machine learning, offering a hybrid approach that bridges the gap between expressive continuous models and efficient discrete ones.

The paper tackles the trade-off between expressiveness and tractability in probabilistic models by proposing continuous mixtures of tractable models with small latent dimensions, which set new state-of-the-art results for tractable models on standard density estimation benchmarks.

Probabilistic models based on continuous latent spaces, such as variational autoencoders, can be understood as uncountable mixture models where components depend continuously on the latent code. They have proven to be expressive tools for generative and probabilistic modelling, but are at odds with tractable probabilistic inference, that is, computing marginals and conditionals of the represented probability distribution. Meanwhile, tractable probabilistic models such as probabilistic circuits (PCs) can be understood as hierarchical discrete mixture models, and thus are capable of performing exact inference efficiently but often show subpar performance in comparison to continuous latent-space models. In this paper, we investigate a hybrid approach, namely continuous mixtures of tractable models with a small latent dimension. While these models are analytically intractable, they are well amenable to numerical integration schemes based on a finite set of integration points. With a large enough number of integration points the approximation becomes de-facto exact. Moreover, for a finite set of integration points, the integration method effectively compiles the continuous mixture into a standard PC. In experiments, we show that this simple scheme proves remarkably effective, as PCs learnt this way set new state of the art for tractable models on many standard density estimation benchmarks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes