Representing Partial Programs with Blended Abstract Semantics
arXiv:2012.12964
Abstract
Synthesizing programs from examples requires searching over a vast, combinatorial space of possible programs. In this search process, a key challenge is representing the behavior of a partially written program before it can be executed, to judge if it is on the right track and predict where to search next. We introduce a general technique for representing partially written programs in a program synthesis engine. We take inspiration from the technique of abstract interpretation, in which an approximate execution model is used to determine if an unfinished program will eventually satisfy a goal specification. Here we learn an approximate execution model implemented as a modular neural network. By constructing compositional program representations that implicitly encode the interpretation semantics of the underlying programming language, we can represent partial programs using a flexible combination of concrete execution state and learned neural representations, using the learned approximate semantics when concrete semantics are not known (in unfinished parts of the program). We show that these hybrid neuro-symbolic representations enable execution-guided synthesizers to use more powerful language constructs, such as loops and higher-order functions, and can be used to synthesize programs more accurately for a given search budget than pure neural approaches in several domains.
arXiv commentICLR 2021
References in corpus (7)
- On the Convergence of Adam and Beyond
- Generative Code Modeling with Graphs
- Coarse-to-Fine Decoding for Neural Semantic Parsing
- Automatic Program Synthesis of Long Programs with a Learned Garbage Collector
- SyGuS-Comp 2016: Results and Analysis
- TF-Coder: Program Synthesis for Tensor Manipulations
- Learning to Represent Programs with Property Signatures