Universal Marginaliser for Deep Amortised Inference for Probabilistic Programs

10/16/2019
by   Robert Walecki, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/12/2018

Universal Marginalizer for Amortised Inference and Embedding of Generative Models

Probabilistic graphical models are powerful tools which allow us to form...
research
10/31/2016

Inference Compilation and Universal Probabilistic Programming

We introduce a method for using deep neural networks to amortize the cos...
research
11/02/2017

A Universal Marginalizer for Amortized Inference in Generative Models

We consider the problem of inference in a causal generative model where ...
research
10/18/2016

Deep Amortized Inference for Probabilistic Programs

Probabilistic programming languages (PPLs) are a powerful modeling tool,...
research
05/19/2022

Foundation Posteriors for Approximate Probabilistic Inference

Probabilistic programs provide an expressive representation language for...
research
10/22/2020

Conditional independence by typing

A central goal of probabilistic programming languages (PPLs) is to separ...
research
06/07/2019

Automatic Reparameterisation of Probabilistic Programs

Probabilistic programming has emerged as a powerful paradigm in statisti...

Please sign up or login with your details

Forgot password? Click here to reset