https://github.com/theo-brown/invariantkernels

Transformation-invariant kernels in GPyTorch
https://github.com/theo-brown/invariantkernels

Last synced: 3 months ago
JSON representation

Transformation-invariant kernels in GPyTorch

• Host: GitHub
• URL: https://github.com/theo-brown/invariantkernels
• Owner: theo-brown
• License: mit
• Created: 2024-03-01T13:39:34.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-10-16T10:05:21.000Z (8 months ago)
• Last Synced: 2024-12-06T21:06:38.687Z (6 months ago)
• Language: Jupyter Notebook
• Size: 131 KB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# invariantkernels

*Transformation-invariant kernels in GPyTorch*

This package provides kernels for Gaussian processes that are invariant to transformations.

The core class is `GroupInvariantKernel`, which can be composed with other GPyTorch kernels to make them invariant to a group of transformations.

Example groups are in [`invariant_kernels/transformation_groups`](./invariantkernels/transformation_groups.py).

#### Citing

The package was developed for the paper *Sample-efficient Bayesian Optimisation Using Known Invariances*, NeurIPS 2024. 

The rest of the code can be found at [theo-brown/bayesopt_with_invariances](https://github.com/theo-brown/bayesopt_with_invariances).