pith. machine review for the scientific record. sign in

arxiv: 1611.01989 · v2 · submitted 2016-11-07 · 💻 cs.LG

Recognition: unknown

DeepCoder: Learning to Write Programs

Authors on Pith no claims yet
classification 💻 cs.LG
keywords approachnetworkneuralproblemsprogramminglearningsearchable
0
0 comments X
read the original abstract

We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to predict properties of the program that generated the outputs from the inputs. We use the neural network's predictions to augment search techniques from the programming languages community, including enumerative search and an SMT-based solver. Empirically, we show that our approach leads to an order of magnitude speedup over the strong non-augmented baselines and a Recurrent Neural Network approach, and that we are able to solve problems of difficulty comparable to the simplest problems on programming competition websites.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis

    cs.CL 2026-05 unverdicted novelty 7.0

    LLM reasoning traces can be compiled into reusable symbolic solvers that achieve high accuracy on program synthesis benchmarks at zero inference cost and transfer to other domains.