Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples

by   Ashwin J. Vijayakumar, et al.

Synthesizing user-intended programs from a small number of input-output examples is a challenging problem with several important applications like spreadsheet manipulation, data wrangling and code refactoring. Existing synthesis systems either completely rely on deductive logic techniques that are extensively hand-engineered or on purely statistical models that need massive amounts of data, and in general fail to provide real-time synthesis on challenging benchmarks. In this work, we propose Neural Guided Deductive Search (NGDS), a hybrid synthesis technique that combines the best of both symbolic logic techniques and statistical models. Thus, it produces programs that satisfy the provided specifications by construction and generalize well on unseen examples, similar to data-driven systems. Our technique effectively utilizes the deductive search framework to reduce the learning problem of the neural component to a simple supervised learning setup. Further, this allows us to both train on sparingly available real-world data and still leverage powerful recurrent neural network encoders. We demonstrate the effectiveness of our method by evaluating on real-world customer scenarios by synthesizing accurate programs with up to 12x speed-up compared to state-of-the-art systems.



page 1

page 2

page 3

page 4


Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis

The use of deep learning techniques has achieved significant progress fo...

BUSTLE: Bottom-up program-Synthesis Through Learning-guided Exploration

Program synthesis is challenging largely because of the difficulty of se...

Neural Guided Constraint Logic Programming for Program Synthesis

Synthesizing programs using example input/outputs is a classic problem i...

On Repair with Probabilistic Attribute Grammars

Program synthesis and repair have emerged as an exciting area of researc...

Quantitative Programming by Examples

Programming-by-Example (PBE) systems synthesize an intended program in s...

Synthesizing Symmetric Lenses

Lenses are programs that can be run both "front to back" and "back to fr...

Synthesizing Optimal Parallelism Placement and Reduction Strategies on Hierarchical Systems for Deep Learning

We present a novel characterization of the mapping of multiple paralleli...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.