TR2025-011

Preference-based Multi-Objective Bayesian Optimization with Gradients

    •  Ip, J.H.S., Chakrabarty, A., Masui Hideyuki, , Mesbah, A., Romeres, D., "Preference-based Multi-Objective Bayesian Optimization with Gradients", NeurIPS Workshop on Bayesian Decision-making and Uncertainty, December 2024.
      BibTeX TR2025-011 PDF
      • @inproceedings{Ip2024dec,
      • author = {Ip, Joshua Hang Sai and Chakrabarty, Ankush and Masui Hideyuki and Mesbah, Ali and Romeres, Diego}},
      • title = {Preference-based Multi-Objective Bayesian Optimization with Gradients},
      • booktitle = {NeurIPS Workshop on Bayesian Decision-making and Uncertainty},
      • year = 2024,
      • month = dec,
      • url = {https://www.merl.com/publications/TR2025-011}
      • }
  • MERL Contacts:
  • Research Area:

    Optimization

Abstract:

We propose PUB-MOBO for personalized multi-objective Bayesian Optimization. PUB-MOBO combines utility-based MOBO with local multi-gradient descent to refine user-preferred solutions to be near-Pareto-optimal. Unlike traditional methods, PUB-MOBO does not require estimating the entire Pareto-front, making it more efficient. Experimental results on synthetic and real-world benchmarks show that PUB-MOBO consistently outperforms existing methods in terms of proximity to the Pareto-front and utility regret.