Abstract
Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, fairness, robustness, and more. Unlike single-objective optimization, which aggregates objectives into a scalar through weighted sums, MOPs focus on generating specific or diverse Pareto solutions and learning the entire Pareto set directly. Existing MOP benchmarks primarily focus on evolutionary algorithms, which are zeroth-order or meta-heuristic methods that fail to leverage higher-order objective information and cannot scale to large models. To address these challenges, we introduce LibMOON, the first multiobjective optimization library supporting state-of-the-art gradient-based methods, offering a fair and comprehensive benchmark, and open-sourced for the community.
| Original language | English |
|---|---|
| Title of host publication | 38th Conference on Neural Information Processing Systems, NeurIPS 2024 |
| Editors | A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, C. Zhang |
| Publisher | Neural information processing systems foundation |
| Number of pages | 19 |
| ISBN (Electronic) | 9798331314385 |
| Publication status | Published - Dec 2024 |
| Event | 38th Conference on Neural Information Processing Systems, NeurIPS 2024 - Vancouver Convention Center , Vancouver, Canada Duration: 9 Dec 2024 → 15 Dec 2024 https://neurips.cc/Conferences/2024 https://openreview.net/group?id=NeurIPS.cc/2024 https://proceedings.neurips.cc/paper_files/paper/2024 |
Publication series
| Name | Advances in Neural Information Processing Systems |
|---|---|
| Publisher | Neural information processing systems foundation |
| Volume | 37 |
| ISSN (Print) | 1049-5258 |
| Name | NeurIPS Proceedings |
|---|
Conference
| Conference | 38th Conference on Neural Information Processing Systems, NeurIPS 2024 |
|---|---|
| Country/Territory | Canada |
| City | Vancouver |
| Period | 9/12/24 → 15/12/24 |
| Internet address |