Reactive Graphs for Efficient Markov Chain Monte Carlo Inference in Probabilistic Programming Languages
For developers of probabilistic programming languages, this work offers an automatic optimization for MCMC inference, though the improvement is incremental.
The paper introduces reactive graphs for probabilistic programs to automatically skip recomputation of unchanged parts during Markov chain Monte Carlo inference, improving efficiency. No concrete speedup numbers are provided.
An important aspect of making inference based on a probabilistic program practical is efficiency; faster evaluation enables more work per unit of time, which can be translated into more precision. Inference via Markov chain Monte Carlo has a property that can be favorably exploited for efficiency: most proposed samples are computed as minor variations of previous samples, i.e., a clever implementation can skip computations pertaining to what is unchanged. This paper provides an approach for automatically translating a probabilistic program to a dynamic graph, reminiscent of functional reactive programming, that explicitly represents data dependencies, enabling proposals to only recompute the parts of the graph that depend on redrawn random variables. The graph-building interface follows familiar functional programming interfaces, which also connect to their expressiveness in terms of probabilistic programming: models using the applicative functor portion express Bayesian networks, while those using monads represent universal probabilistic programming languages.