evosax: JAX-based Evolution Strategies
This work addresses the scalability problem for researchers in evolutionary optimization by providing a tool to leverage hardware accelerators, though it is incremental as it builds on existing algorithms with new implementation methods.
The authors tackled the challenge of scaling evolutionary computation to modern hardware accelerators by releasing evosax, a JAX-based library that implements 30 evolutionary optimization algorithms, enabling direct execution on GPUs/TPUs with automatic vectorization and parallelization through a simple API.
The deep learning revolution has greatly been accelerated by the 'hardware lottery': Recent advances in modern hardware accelerators and compilers paved the way for large-scale batch gradient optimization. Evolutionary optimization, on the other hand, has mainly relied on CPU-parallelism, e.g. using Dask scheduling and distributed multi-host infrastructure. Here we argue that also modern evolutionary computation can significantly benefit from the massive computational throughput provided by GPUs and TPUs. In order to better harness these resources and to enable the next generation of black-box optimization algorithms, we release evosax: A JAX-based library of evolution strategies which allows researchers to leverage powerful function transformations such as just-in-time compilation, automatic vectorization and hardware parallelization. evosax implements 30 evolutionary optimization algorithms including finite-difference-based, estimation-of-distribution evolution strategies and various genetic algorithms. Every single algorithm can directly be executed on hardware accelerators and automatically vectorized or parallelized across devices using a single line of code. It is designed in a modular fashion and allows for flexible usage via a simple ask-evaluate-tell API. We thereby hope to facilitate a new wave of scalable evolutionary optimization algorithms.