Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 39(18), 19677-19685., 2025
We propose a novel approach called SVH-PSL, which integrates Stein Variational Gradient Descent (SVGD) with Hypernetworks for efficient Pareto set learning. Our method addresses the issues of fragmented surrogate models and pseudo-local optima by collectively moving particles in a manner that smooths out the solution space. The particles interact with each other through a kernel function, which helps maintain diversity and encourages the exploration of underexplored regions. This kernel-based interaction prevents particles from clustering around pseudo-local optima and promotes convergence towards globally optimal solutions.
Recommended citation: Nguyen, M.-D., Dinh, P. M., Nguyen, Q.-H., Hoang, L. P., & Le, D. D. (2025). Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks. Proceedings of the AAAI Conference on Artificial Intelligence, 39(18), 19677-19685. https://doi.org/10.1609/aaai.v39i18.34167
Download Paper