Sharp Convergence of Wasserstein Gradient Flows for Spectrally Nonnegative Interaction Energies

@misc{lin2026sharp,
  title = {{Sharp Convergence of Wasserstein Gradient Flows for Spectrally Nonnegative Interaction Energies}},
  author = {Zhengjiang Lin and Philippe Rigollet},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.27008},
  eprint = {2609.27008},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27008},
}

TY  - UNPB
TI  - Sharp Convergence of Wasserstein Gradient Flows for Spectrally Nonnegative Interaction Energies
AU  - Zhengjiang Lin
AU  - Philippe Rigollet
PY  - 2026
DA  - 2026/09/22
PB  - arXiv
DO  - 10.48550/arxiv.2609.27008
UR  - https://arxiv.org/abs/2609.27008
AB  - We study the long-time behavior of Wasserstein gradient flows for interaction energies E[μ] = 1/2iint_M× MK(x,y) dμ(x) dμ(y) on a closed manifold M. For kernels diagonal in a Laplace eigenbasis with nonnegative spectral coefficients, we prove a differential inequality relating the relative entropy to the energy gap. Consequently, for any nonnegative initial density u_0∈ L^p(M), p>1, the energy gap is integrable in time and satisfies E[μ_t]−E_min=o(t^−1). If all spectral coefficients are positive, the flow converges weakly to the constant measure. These interaction energies need not be geodesically convex in Wasserstein space, and the associated flows contain no diffusion; their global convergence therefore does not follow from standard Wasserstein gradient flow theory. The kernels covered by our results include zonal kernels on spheres, kernels arising in transformer models, regularized Riesz kernels, and inverse fractional Laplacian kernels. We also investigate the sharpness of the o(t^−1) rate. For any smooth kernel in this class with infinitely many positive spectral coefficients and any δ>0, we construct a solution of the linearized flow whose energy is comparable to t^−1−δ along a sequence of times tending to infinity. Moreover, for any δ>0, by choosing a suitable inverse fractional Laplacian kernel on the flat torus, we construct an exact solution of the nonlinear Wasserstein gradient flow whose energy is comparable to t^−1−δ. The nonlinear construction is based on uniform-in-time estimates for the evolution of the dyadic Fourier coefficient blocks and a blockwise energy-persistence argument. These estimates also yield a uniform-in-time quantitative comparison between the nonlinear Wasserstein gradient flow and its linearization.
ER  -