mlsanityData to 7 Oct 2026

Kozax: Flexible and Scalable Genetic Programming in JAX

arXiv 2502.03047 ↗First posted 5 Feb 2025cs.NE cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Genetic programming is an optimization algorithm inspired by evolution which automatically evolves the structure of interpretable computer programs. The fitness evaluation in genetic programming suffers from high computational requirements, limiting the performance on difficult problems. Consequently, there is no efficient genetic programming framework that is usable for a wide range of tasks. To this end, we developed Kozax, a genetic programming framework that evolves symbolic expressions for arbitrary problems. We implemented Kozax using JAX, a framework for high-performance and scalable machine learning, which allows the fitness evaluation to scale efficiently to large populations or datasets on GPU. Furthermore, Kozax offers constant optimization, custom operator definition and simultaneous evolution of multiple trees. We demonstrate successful applications of Kozax to discover equations of natural laws, recover equations of hidden dynamic variables, evolve a control policy and optimize an objective function. Overall, Kozax provides a general, fast, and scalable library to optimize white-box solutions in the realm of scientific computing.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 13 of its 48 references that are in the map. First posted on arXiv 5 Feb 2025.

Builds on

13 of 48 references.

References · 13

  1. 2021Contemporary Symbolic Regression Methods and their Relative Performancecited by 209
  2. 2020Explainable Reinforcement Learning: A Surveycited by 139
  3. 2019Meta-Learning via Learned Losscited by 60
  4. 2017Interpretable Policies for Reinforcement Learning by Genetic Programmingcited by 47
  5. 2022evosax: JAX-based Evolution Strategiescited by 39
  6. 2023Interpretable Machine Learning for Science with PySR and SymbolicRegression.jlcited by 36
  7. 2022EvoJAX: Hardware-Accelerated Neuroevolutioncited by 29
  8. 2023EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computationcited by 16
  9. 2021Accelerating Genetic Programming using GPUscited by 3
  10. 2025Enabling Population-Level Parallelism in Tree-Based Genetic Programming for GPU Accelerationcited by 3
  11. 2016Faster GPU Based Genetic Programming Using A Two Dimensional Stackcited by 2
  12. 2021GSGP-CUDA -- a CUDA framework for Geometric Semantic Genetic Programmingcited by 1
1 more
  1. 2024Fast and Efficient Local Search for Genetic Programming Based Loss Function Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Neuromorphic Intelligencecited by 1
  2. 2026Evolving Layer-Specific Scalar Functions for Hardware-Aware Transformer Adaptationcited by 0
  3. 2026Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic Programmingcited by 0