Skip to content

spectraldani/infinite-neural-operator

Repository files navigation

Infinite Neural Operators: Gaussian processes on functions

This repository contains implementation of the infinite-width Bayesian Neural operator in the publication

Daniel Augusto de Souza, Yuchen Zhu, Henry Jake Cunningham, Yuri Saporito, Diego Mesquita, Marc Peter Deisenroth. (2025). Infinite Neural Operators: Gaussian processes on functions. In: Advances in Neural Information Processing Systems (NeurIPS) 39

The paper can be downloaded from ArXiv.

Install

This library was implemented against Python 3.11. To install it and its dependencies, please clone or download the repository using pip:

pip install git+https://github.com/spectraldani/infinite-neural-operator.git

Citation

If you use the code in this repository for your research, please cite the paper as follows:

@inproceedings{desouza2025infinite,
    title = {Infinite Neural Operators: Gaussian processes on functions},
    author = {de Souza, Daniel Augusto and Zhu, Yuchen and Cunningham, Henry Jake and Saporito, Yuri and Mesquita, Diego and Deisenroth, Marc Peter},
    year = {2025},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
}

About

Reference implementation for "Infinite Neural Operators: Gaussian processes on functions" (NeurIPS 2025)

Topics

Resources

License

Stars

Watchers

Forks