HyperNOs: automated and parallel library for neural operators research

Abstract This paper introduces HyperNOs, a PyTorch library designed to streamline and automate the process of exploring neural operators, with a special focus on hyperparameter optimization for comprehensive and exhaustive exploration. In particular, HyperNOs leverages state-of-the-art optimization algorithms and parallel computing implemented in the Ray-tune library to efficiently explore the hyperparameter space of neural operators. We also implement several features for studying neural operators with a user-friendly interface, such as the ability to train the model with a fixed number of parameters or to train the model with multiple datasets and different resolutions. We integrate Fourier neural operators and convolutional neural operators in our library, achieving state-of-the-art results on many representative benchmarks, demonstrating the capabilities of HyperNOs to handle real datasets and modern architectures. The library is designed for ease of use with the provided model and datasets, but also to be extended to use new datasets and custom neural operator architectures.