Trust-Region Optimization for Smooth Potential-Interaction Energies in Wasserstein Space
Abstract
Finding low-energy configurations of interacting particles and approximating probability distributions lead to the minimization of potential-interaction energies in Wasserstein space. These energies can be nonconvex, making it important to exploit second-order information while controlling the reliability of local approximations. We study trust-region optimization of smooth potential-interaction energies on the Wasserstein space of probability measures with finite second moment. The method uses a quadratic model along pushforward curves, an L2(ρ) step radius, and a Steihaug-Toint subsolver with an explicit self-adjoint second-variation operator. A ratio test determines acceptance and guides the radius update. Under a lower energy bound and globally bounded Hessians of the potential and interaction kernel, we prove that the objective is nonincreasing, the Wasserstein-gradient norms converge to zero, and an ε-stationary iterate is reached within O(ε−2) total outer trials, including rejected trials. If the potential is quadratically coercive, every weak accumulation point is stationary. The analysis applies to arbitrary initial measures with finite second moment. For empirical measures, the iteration is a finite-dimensional trust-region method in the L2(ρN) inner product, with complexity constants independent of particle number and dimension when the initial objective gaps are uniformly bounded. Numerical experiments include a smooth soft-particle energy, maximum-mean-discrepancy minimization for non-Gaussian targets, component ablations, and scaling studies in particle number and dimension.
Related
- Sharp Convergence of Wasserstein Gradient Flows for Spectrally Nonnegative Interaction Energies
- Dissipative solutions for fibred Wasserstein gradient flows of Cahn-Hilliard-type energies
- Higher-Order Sensitivity Analysis of Wasserstein and Adapted Wasserstein Distributionally Robust Optimization Problems
- First-Order Methods for Wasserstein Distributionally Robust Constrained Optimization
- A Note on the NP-Hardness on Quadratic Optimization over Doubly Stochastic Matrices and the Gromov-Wasserstein Problem
BibTeX
@misc{wan2026trustregion,
title = {{Trust-Region Optimization for Smooth Potential-Interaction Energies in Wasserstein Space}},
author = {You Wan and Ting Gao and Jinqiao Duan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.08883},
eprint = {2610.08883},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.08883},
}
RIS
TY - UNPB
TI - Trust-Region Optimization for Smooth Potential-Interaction Energies in Wasserstein Space
AU - You Wan
AU - Ting Gao
AU - Jinqiao Duan
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2610.08883
UR - https://arxiv.org/abs/2610.08883
AB - Finding low-energy configurations of interacting particles and approximating probability distributions lead to the minimization of potential-interaction energies in Wasserstein space. These energies can be nonconvex, making it important to exploit second-order information while controlling the reliability of local approximations. We study trust-region optimization of smooth potential-interaction energies on the Wasserstein space of probability measures with finite second moment. The method uses a quadratic model along pushforward curves, an L^2(ρ) step radius, and a Steihaug-Toint subsolver with an explicit self-adjoint second-variation operator. A ratio test determines acceptance and guides the radius update. Under a lower energy bound and globally bounded Hessians of the potential and interaction kernel, we prove that the objective is nonincreasing, the Wasserstein-gradient norms converge to zero, and an ε-stationary iterate is reached within O(ε^−2) total outer trials, including rejected trials. If the potential is quadratically coercive, every weak accumulation point is stationary. The analysis applies to arbitrary initial measures with finite second moment. For empirical measures, the iteration is a finite-dimensional trust-region method in the L^2(ρ_N) inner product, with complexity constants independent of particle number and dimension when the initial objective gaps are uniformly bounded. Numerical experiments include a smooth soft-particle energy, maximum-mean-discrepancy minimization for non-Gaussian targets, component ablations, and scaling studies in particle number and dimension.
ER -