# Learning to superoptimize programs - Workshop Version

arXiv: https://arxiv.org/abs/1612.01094 · HTML: https://mlsanity.com/paper/1612.01094/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2016.

## Built on by (most cited first, 1 of 1)

- [Autoencoders as Tools for Program Synthesis](https://mlsanity.com/paper/2108.07129/) (2021)

## Abstract (arXiv)

Superoptimization requires the estimation of the best program for a given computational task. In order to deal with large programs, superoptimization techniques perform a stochastic search. This involves proposing a modification of the current program, which is accepted or rejected based on the improvement achieved. The state of the art method uses uniform proposal distributions, which fails to exploit the problem structure to the fullest. To alleviate this deficiency, we learn a proposal distribution over possible modifications using Reinforcement Learning. We provide convincing results on the superoptimization of "Hacker's Delight" programs.