Using probabilistic programs as proposals
This addresses the problem of slow inference for practitioners in probabilistic modeling by enabling more efficient, user-guided proposals, though it is incremental as it builds on existing probabilistic programming and neural network methods.
The paper tackles the inefficiency of generic proposals in Monte Carlo inference by introducing proposal programs, which allow users to encode posterior knowledge as samplers in probabilistic programming languages, resulting in accelerated inference without sacrificing asymptotic consistency.
Monte Carlo inference has asymptotic guarantees, but can be slow when using generic proposals. Handcrafted proposals that rely on user knowledge about the posterior distribution can be efficient, but are difficult to derive and implement. This paper proposes to let users express their posterior knowledge in the form of proposal programs, which are samplers written in probabilistic programming languages. One strategy for writing good proposal programs is to combine domain-specific heuristic algorithms with neural network models. The heuristics identify high probability regions, and the neural networks model the posterior uncertainty around the outputs of the algorithm. Proposal programs can be used as proposal distributions in importance sampling and Metropolis-Hastings samplers without sacrificing asymptotic consistency, and can be optimized offline using inference compilation. Support for optimizing and using proposal programs is easily implemented in a sampling-based probabilistic programming runtime. The paper illustrates the proposed technique with a proposal program that combines RANSAC and neural networks to accelerate inference in a Bayesian linear regression with outliers model.