Meta-Learning an Inference Algorithm for Probabilistic Programs
This addresses the challenge of scalable inference for probabilistic programming, though it is incremental as it builds on existing meta-learning and neural network techniques.
The authors tackled the problem of learning an efficient posterior-inference algorithm for probabilistic programs by meta-learning a white-box method that uses neural networks per atomic command, achieving better test-time efficiency than alternatives like HMC in some cases.
We present a meta-algorithm for learning a posterior-inference algorithm for restricted probabilistic programs. Our meta-algorithm takes a training set of probabilistic programs that describe models with observations, and attempts to learn an efficient method for inferring the posterior of a similar program. A key feature of our approach is the use of what we call a white-box inference algorithm that extracts information directly from model descriptions themselves, given as programs. Concretely, our white-box inference algorithm is equipped with multiple neural networks, one for each type of atomic command, and computes an approximate posterior of a given probabilistic program by analysing individual atomic commands in the program using these networks. The parameters of the networks are learnt from a training set by our meta-algorithm. We empirically demonstrate that the learnt inference algorithm generalises well to programs that are new in terms of both parameters and model structures, and report cases where our approach achieves greater test-time efficiency than alternative approaches such as HMC. The overall results show the promise as well as remaining challenges of our approach.