A Jump-Modified Wasserstein Gradient Flow for Maximum Mean Discrepancy with Energy Kernels
Abstract
We study a jump-modified Wasserstein gradient flow of the squared maximum mean discrepancy generated by the energy kernels K(z)=−|z|q, 0<q<2, in every dimension d≥2 as well as the one-dimensional range 1≤ q<2. Under subcritical density and finite-moment assumptions, we prove global well-posedness. The added jumps transfer mass toward smaller values of the first variation and dissipate the same MMD energy as the transport term. Under our hypotheses on the target and jump rates, every Borel probability measure with finite MMD energy and zero jump dissipation is equal to the target. Combining this rigidity with compactness and a second-moment identity yields convergence to the target from finite-second-moment data, without additional uniform-in-time density or moment assumptions. We also construct a global collision-free particle process whose energy is nonincreasing along each path. A quantitative mean-field estimate applies to general initial empirical approximations, including deterministic configurations; propagation of chaos for exchangeable data and long-time target approximation follow as consequences.
Related
- Equidistribution of number theoretic point sets in the torus and the sphere in Wasserstein metric and L2 discrepancy
- Projected and Reflected Sliced Wasserstein Kernels for Persistence Diagrams
- Pontryagin maximum principle for non-smooth state-constrained control problems over Wasserstein spaces
- Wasserstein mirror gradient flow as the limit of the Sinkhorn algorithm
- Early stopping of stochastic variance reduced gradient for linear inverse problems by the discrepancy principle
BibTeX
@misc{desai2026jumpmodified,
title = {{A Jump-Modified Wasserstein Gradient Flow for Maximum Mean Discrepancy with Energy Kernels}},
author = {Ansh Desai and Jason Liu and Srujan Roplekar and Matthew Rosenzweig},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.29007},
eprint = {2610.29007},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.29007},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Jump-Modified Wasserstein Gradient Flow for Maximum Mean Discrepancy with Energy Kernels
AU - Ansh Desai
AU - Jason Liu
AU - Srujan Roplekar
AU - Matthew Rosenzweig
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2610.29007
UR - https://arxiv.org/abs/2610.29007
AB - We study a jump-modified Wasserstein gradient flow of the squared maximum mean discrepancy generated by the energy kernels K(z)=−|z|^q, 0<q<2, in every dimension d≥2 as well as the one-dimensional range 1≤ q<2. Under subcritical density and finite-moment assumptions, we prove global well-posedness. The added jumps transfer mass toward smaller values of the first variation and dissipate the same MMD energy as the transport term. Under our hypotheses on the target and jump rates, every Borel probability measure with finite MMD energy and zero jump dissipation is equal to the target. Combining this rigidity with compactness and a second-moment identity yields convergence to the target from finite-second-moment data, without additional uniform-in-time density or moment assumptions. We also construct a global collision-free particle process whose energy is nonincreasing along each path. A quantitative mean-field estimate applies to general initial empirical approximations, including deterministic configurations; propagation of chaos for exchangeable data and long-time target approximation follow as consequences.
ER -