Universal Marginaliser for Deep Amortised Inference for Probabilistic Programs
arXiv:1910.07474
Abstract
Probabilistic programming languages (PPLs) are powerful modelling tools which allow to formalise our knowledge about the world and reason about its inherent uncertainty. Inference methods used in PPL can be computationally costly due to significant time burden and/or storage requirements; or they can lack theoretical guarantees of convergence and accuracy when applied to large scale graphical models. To this end, we present the Universal Marginaliser (UM), a novel method for amortised inference, in PPL. We show how combining samples drawn from the original probabilistic program prior with an appropriate augmentation method allows us to train one neural network to approximate any of the corresponding conditional marginal distributions, with any separation into latent and observed variables, and thus amortise the cost of inference. Finally, we benchmark the method on multiple probabilistic programs, in Pyro, with different model structure.
References in corpus (7)
- MADE: Masked Autoencoder for Distribution Estimation
- Deep Amortized Inference for Probabilistic Programs
- Recognition Networks for Approximate Inference in BN20 Networks
- Learning about an exponential amount of conditional distributions
- Data-driven Sequential Monte Carlo in Probabilistic Programming
- Applications of Probabilistic Programming (Master's thesis, 2015)
- Universal Marginalizer for Amortised Inference and Embedding of Generative Models