mlsanityData to 14 Oct 2026

Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization

arXiv 2501.19342 ↗First posted 31 Jan 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In multi-objective black-box optimization, the goal is typically to find solutions that optimize a set of T black-box objective functions, f1, ldots fT, simultaneously. Traditional approaches often seek a single Pareto-optimal set that balances trade-offs among all objectives. In contrast, we consider a problem setting that departs from this paradigm: finding a small set of K < T solutions, that collectively "cover" the T objectives. A set of solutions is defined as "covering" if, for each objective f1, ldots fT, there is at least one good solution. A motivating example for this problem setting occurs in drug design. For example, we may have T pathogens and aim to identify a set of K < T antibiotics such that at least one antibiotic can be used to treat each pathogen. This problem, known as coverage optimization, has yet to be tackled with the Bayesian optimization (BO) framework. To fill this void, we develop Multi-Objective Coverage Bayesian Optimization (MOCOBO), a BO algorithm for solving coverage optimization. Our approach is based on a new acquisition function reminiscent of expected improvement in the vanilla BO setup. We demonstrate the performance of our method on high-dimensional black-box optimization tasks, including applications in peptide and molecular design. Results show that the coverage of the K < T solutions found by MOCOBO matches or nearly matches the coverage of T solutions obtained by optimizing each objective individually. Furthermore, in in vitro experiments, the peptides found by MOCOBO exhibited high potency against drug-resistant pathogens, further demonstrating the potential of MOCOBO for drug discovery. All of our code is publicly available at the following link: https://github.com/nataliemaus/mocobo.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 89 references that are in the map. First posted on arXiv 31 Jan 2025.

Builds on

39 of 89 references.

References · 39

  1. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  2. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  3. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  4. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 609
  5. 2017NIMA: Neural Image Assessmentcited by 389
  6. 2019Scalable Global Optimization via Local Bayesian Optimizationcited by 374
  7. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 297
  8. 2017Grammar Variational Autoencodercited by 285
  9. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  10. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 226
  11. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 166
  12. 2021Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020cited by 148
27 more
  1. 2020Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retrainingcited by 123
  2. 2017Batched Large-scale Bayesian Optimization in High-dimensional Spacescited by 117
  3. 2018Maximizing acquisition functions for Bayesian optimizationcited by 114
  4. 2017Constrained Bayesian Optimization with Noisy Experimentscited by 104
  5. 2022Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoderscited by 102
  6. 2016Stochastic Variational Deep Kernel Learningcited by 93
  7. 2024Vanilla Bayesian Optimization Performs Great in High Dimensionscited by 92
  8. 2015Predictive Entropy Search for Multi-objective Bayesian Optimizationcited by 88
  9. 2021Multi-Objective Bayesian Optimization over High-Dimensional Search Spacescited by 87
  10. 2020Scalable Constrained Bayesian Optimizationcited by 84
  11. 2020Max-value Entropy Search for Multi-Objective Bayesian Optimization with Constraintscited by 81
  12. 2022Local Latent Space Bayesian Optimization over Structured Inputscited by 79
  13. 2017Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Spacecited by 76
  14. 2021High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learningcited by 54
  15. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  16. 2016Parallel Bayesian Global Optimization of Expensive Functionscited by 44
  17. 2022Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimizationcited by 44
  18. 2022Discovering Many Diverse Solutions with Bayesian Optimizationcited by 31
  19. 2020Sequential Gallery for Interactive Visual Design Optimizationcited by 25
  20. 2020Good practices for Bayesian Optimization of high dimensional structured spacescited by 24
  21. 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequencescited by 23
  22. 2023Advancing Bayesian Optimization via Learning Correlated Latent Spacecited by 18
  23. 2019Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimizationcited by 16
  24. 2024Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimizationcited by 16
  25. 2024Many-Objective Multi-Solution Transportcited by 5
  26. 2024Efficient Algorithms for Sum-of-Minimum Optimizationcited by 4
  27. 2023Achieving Diversity in Objective Space for Sample-efficient Search of Multiobjective Optimization Problemscited by 1

Built on by

Not cited yet.