TensorGP -- Genetic Programming Engine in TensorFlow

TL;DR

This paper introduces TensorGP, a genetic programming engine built on TensorFlow, which leverages data vectorization and fitness caching to significantly improve performance, achieving up to 100x speedups over traditional methods.

Contribution

The paper presents TensorGP, a novel TensorFlow-based genetic programming engine that exploits eager execution for substantial performance enhancements.

Findings

Performance gains of up to two orders of magnitude.

Effective use of data vectorization and fitness caching.

Superior scalability on dedicated hardware.

Abstract

In this paper, we resort to the TensorFlow framework to investigate the benefits of applying data vectorization and fitness caching methods to domain evaluation in Genetic Programming. For this purpose, an independent engine was developed, TensorGP, along with a testing suite to extract comparative timing results across different architectures and amongst both iterative and vectorized approaches. Our performance benchmarks demonstrate that by exploiting the TensorFlow eager execution model, performance gains of up to two orders of magnitude can be achieved on a parallel approach running on dedicated hardware when compared to a standard iterative approach.