Summary - TerpreT: A Probabilistic Programming Language for Program Induction

• Main Authors: Gaunt, Alexander L, Brockschmidt, Marc, Singh, Rishabh, Kushman, Nate, Kohli, Pushmeet, Taylor, Jonathan, Tarlow, Daniel
• Format: Journal Article
• Language: English
• Published: 02.12.2016
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning; Computer Science - Neural and Evolutionary Computing
• DOI: 10.48550/arxiv.1612.00817

We study machine learning formulations of inductive program synthesis; that is, given input-output examples, synthesize source code that maps inputs to corresponding outputs. Our key contribution is TerpreT, a domain-specific language for expressing program synthesis problems. A TerpreT model is composed of a specification of a program representation and an interpreter that describes how programs map inputs to outputs. The inference task is to observe a set of input-output examples and infer the underlying program. From a TerpreT model we automatically perform inference using four different back-ends: gradient descent (thus each TerpreT model can be seen as defining a differentiable interpreter), linear program (LP) relaxations for graphical models, discrete satisfiability solving, and the Sketch program synthesis system. TerpreT has two main benefits. First, it enables rapid exploration of a range of domains, program representations, and interpreter models. Second, it separates the model specification from the inference algorithm, allowing proper comparisons between different approaches to inference. We illustrate the value of TerpreT by developing several interpreter models and performing an extensive empirical comparison between alternative inference algorithms on a variety of program models. To our knowledge, this is the first work to compare gradient-based search over program space to traditional search-based alternatives. Our key empirical finding is that constraint solvers dominate the gradient descent and LP-based formulations. This is a workshop summary of a longer report at arXiv:1608.04428