https://github.com/aaltoml/t-svgp

Codes for 'Dual Parameterization of Sparse Variational Gaussian Processes' (NeurIPS 2021)

https://github.com/aaltoml/t-svgp

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.9%) to scientific vocabulary

Keywords

gaussian-processes variational-inference
Last synced: 9 months ago · JSON representation

Repository

Codes for 'Dual Parameterization of Sparse Variational Gaussian Processes' (NeurIPS 2021)

Basic Info
  • Host: GitHub
  • Owner: AaltoML
  • License: mit
  • Language: Python
  • Default Branch: develop
  • Homepage:
  • Size: 1.59 MB
Statistics
  • Stars: 7
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Topics
gaussian-processes variational-inference
Created over 4 years ago · Last pushed over 4 years ago
Metadata Files
Readme License

README.md

Dual Parameterization of Sparse Variational Gaussian Processes

Quality checks and Tests Docs build

Documentation | Notebooks | API reference

Introduction

This repository is the official implementation of the methods in the publication:

  • V. Adam, P.E. Chang, M.E. Khan, and A. Solin (2021). Dual Parameterization of Sparse Variational Gaussian Processes. In Advances in Neural Information Processing Systems (NeurIPS). [arXiv]

The paper's main result shows that an alternative (dual) parameterization for SVGP models leads to a better objective for learning and allows for faster inference via natural gradient descent.

Repository structure

The repository has the following folder structure:

  • scr contains the source code
  • experiments contains scripts to reproduce some of the experiments presented in the paper
  • docs contains documentation in the form of notebooks and an api reference.
  • tests contains unit and integration tests for the source code

Installation

We recommend using Python version 3.7.3 and pip version 20.1.1. To install the package, run:

bash pip install -e .

To run the tests, notebooks, build the docs or run the experiments, install the dependencies:

bash pip install \ -r tests_requirements.txt \ -r notebook_requirements.txt \ -r docs/docs_requirements.txt \ -e .

Notebooks

To build the notebooks from source, use jupytext: bash jupytext --to notebook [filename].py

Citation

If you use the code in this repository for your research, please cite the paper as follows: bibtex @inproceedings{adam2021dual, title={Dual Parameterization of Sparse Variational {G}aussian Processes}, author={Adam, Vincent and Chang, Paul Edmund and Khan, Mohammad Emtiyaz and Solin, Arno}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2021} }

Contributing

For all correspondence, please contact vincenta@gatsby.ucl.ac.uk.

License

This software is provided under the MIT license.

Owner

  • Name: AaltoML
  • Login: AaltoML
  • Kind: organization
  • Location: Finland

Machine learning group at Aalto University lead by Prof. Solin

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2

Dependencies

docs/docs_requirements.txt pypi
  • ipython *
  • jupytext *
  • nbsphinx *
  • pandoc *
  • pydata-sphinx-theme *
  • sphinx *
  • sphinx-autoapi *
  • sphinxcontrib-bibtex *
experiments/experiments_requirements.txt pypi
  • matplotlib *
  • pandas *
  • scikit-learn *
notebook_requirements.txt pypi
  • jupyter *
  • matplotlib *
  • pandas *
  • scikit-learn *
tests_requirements.txt pypi
  • black ==20.8b1 test
  • codecov * test
  • flake8 ==3.8.4 test
  • ipykernel * test
  • isort ==5.6.4 test
  • jupyter_client * test
  • jupytext * test
  • mypy ==0.770 test
  • nbconvert * test
  • nbformat * test
  • pytest * test
  • pytest-cov * test
  • pytest-mock * test
  • pytest-random-order * test
  • tornado * test
  • tqdm * test