Data

Tools

Indexes

Applications

Experiments

Open Source Science

momfbo-algorithm

A Multi-objective Multi-fidelity acquisition function for Bayesian optimization based on EHVI method.

https://github.com/pulse-ml/momfbo-algorithm

Science Score: 54.0%

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

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .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 (5.6%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

A Multi-objective Multi-fidelity acquisition function for Bayesian optimization based on EHVI method.

Basic Info
  • Host: GitHub
  • Owner: PULSE-ML
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 379 KB
Statistics
  • Stars: 10
  • Watchers: 1
  • Forks: 2
  • Open Issues: 0
  • Releases: 0
Created about 4 years ago · Last pushed almost 4 years ago
Metadata Files
Readme Citation

README.md

Multi-objective, multi-fidelity (MOMF) Bayesian Optimization (BO) Algorithm

A method for simultaneous multi-objective and multi-fidelity Bayesian optimization based on expected hypervolume improvement. For more details on the Algorithm please see the following paper outlining the basic functioning.

Faran Irshad & Andreas Döpp, Expected hypervolume improvement for simultaneous multi-objective and multi-fidelity optimization, arXiv:2112.13901 (2021) https://arxiv.org/abs/2112.13901

This algorithm makes use of BoTorch (https://botorch.org), which is a Bayesian Optimization framework developed on the Pytorch domain. The acquisition function is available now in the recent version of botorch. To run the tutorial notebook you can import the MOMF acquisiton function from the botorch/acquisition/multiobjective/multifidelity.py. The test function for MOMF can also be found in botorch/testfunctions/multiobjectivemultifidelity.py while there is a complete tutorial notebook available under botorch/tutorials/MultiobjectivemultifidelityBO.ipynb. This tutorial notebook already imports the MOMF and the test functions and demonstrates the working of the MOMF acquisition function

Owner

  • Login: PULSE-ML
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Expected hypervolume improvement for
  simultaneousmulti-objective and multi-fidelity
  optimization
message: >-
  If you use this addition, please cite the
  associated paper.
type: software
authors:
  - given-names: Faran
    family-names: Irshad
    email: faran.irshad@lmu.de
    affiliation: 'Faculty of Physics, LMU Munich'
  - given-names: Andreas
    family-names: Döpp
    email: a.doepp@lmu.de
    affiliation: 'Faculty of Physics, LMU Munich'
  - given-names: 'Stefan '
    family-names: Karsch
    email: stefan.karsch@lmu.de
    affiliation: 'Faculty of Physics, LMU Munich'

GitHub Events

Total
  • Watch event: 3
Last Year
  • Watch event: 3