Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow
International Conference on Artificial Intelligence and Statistics(2023)
摘要
Multi-objective optimization (MOO) aims to optimize multiple, possibly
conflicting objectives with widespread applications. We introduce a novel
interacting particle method for MOO inspired by molecular dynamics simulations.
Our approach combines overdamped Langevin and birth-death dynamics,
incorporating a "dominance potential" to steer particles toward global Pareto
optimality. In contrast to previous methods, our method is able to relocate
dominated particles, making it particularly adept at managing Pareto fronts of
complicated geometries. Our method is also theoretically grounded as a
Wasserstein-Fisher-Rao gradient flow with convergence guarantees. Extensive
experiments confirm that our approach outperforms state-of-the-art methods on
challenging synthetic and real-world datasets.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要