Inference Compilation and Universal Probabilistic Programming

Abstract

We introduce a method for using deep neural networks to amortize the cost of inference in models from the family induced by universal probabilistic programming languages, establishing a framework that combines the strengths of probabilistic programming and deep learning methods. We call what we do "compilation of inference" because our method transforms a denotational specification of an inference problem in the form of a probabilistic program written in a universal programming language into a trained neural network denoted in a neural network specification language. When at test time this neural network is fed observational data and executed, it performs approximate inference in the original model specified by the probabilistic program. Our training objective and learning procedure are designed to allow the trained neural network to be used as a proposal distribution in a sequential importance sampling inference engine. We illustrate our method on mixture models and Captcha solving and show significant speedups in the efficiency of inference.

11 pages, 6 figures

Cited by in corpus (16)

• The frontier of simulation-based inference
• Mining gold from implicit models to improve likelihood-free inference
• Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows
• Benchmarking Simulation-Based Inference
• Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
• Reframing Jet Physics with New Computational Methods
• Comparison of Affine and Rational Quadratic Spline Coupling and Autoregressive Flows through Robust Statistical Tests
• Neural Density Estimation and Likelihood-free Inference
• Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
• Unifying AI Algorithms with Probabilistic Programming using Implicitly Defined Representations
• Amortized Probabilistic Detection of Communities in Graphs
• Control-Data Separation and Logical Condition Propagation for Efficient Inference on Probabilistic Programs
• Universal Policies for Software-Defined MDPs
• Meta-Learning an Inference Algorithm for Probabilistic Programs
• Accelerating Metropolis-Hastings with Lightweight Inference Compilation
• Towards Verified Stochastic Variational Inference for Probabilistic Programs