Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization

This repository contains the python implementation for USeMO from the AAAI 2020 paper "Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization".

The implementation handles automatically the batch version of the algorithm by setting the variable "batch_size" to a number higher than 1.

Requirements

The code is implemented in Python and requires the following packages:

1. sobol_seq

2. platypus

3. sklearn.gaussian_process

4. pygmo

Citation

If you use this code please cite our paper:

@inproceedings{belakaria2020uncertainty,
  title={Uncertainty-aware search framework for multi-objective Bayesian optimization},
  author={Belakaria, Syrine and Deshwal, Aryan and Jayakodi, Nitthilan Kannappan and Doppa, Janardhan Rao},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={34},
  number={06},
  pages={10044--10052},
  year={2020}
}