charlesxuuu / EPOSearch

Exact Pareto Optimal solutions for preference based Multi-Objective Optimization

Exact Pareto Optimal Search

This repository contains code for all the experiments in the ICML 2020 paper

Multi-Task Learning with User Preferences: Gradient Descent with Controlled Ascent in Pareto Optimization

Video

You can get an intuitive understanding of the algorithm from this video.

Citation

If you find this work useful, please cite our paper.

@InProceedings{pmlr-v119-mahapatra20a,
  title = 	 {Multi-Task Learning with User Preferences: Gradient Descent with Controlled Ascent in Pareto Optimization},
  author =       {Mahapatra, Debabrata and Rajan, Vaibhav},
  booktitle = 	 {Proceedings of the 37th International Conference on Machine Learning},
  pages = 	 {6597--6607},
  year = 	 {2020},
  editor = 	 {III, Hal Daumé and Singh, Aarti},
  volume = 	 {119},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--18 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v119/mahapatra20a/mahapatra20a.pdf},
  url = 	 {http://proceedings.mlr.press/v119/mahapatra20a.html},
}