# Gradient Flows of Potential Energies in the Geometry of Sinkhorn Divergences

arXiv: https://arxiv.org/abs/2511.14278 · HTML: https://mlsanity.com/paper/2511.14278/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2025.

## Built on by (most cited first, 4 of 4)

- [Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL Divergences](https://mlsanity.com/paper/2602.02250/) (2026)
- [Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics](https://mlsanity.com/paper/2603.20656/) (2026)
- [Variational Inference via Entropic Transport Descent](https://mlsanity.com/paper/2606.25265/) (2026)
- [On the convergence of graph Laplacians with a symmetric divergence](https://mlsanity.com/paper/2607.05892/) (2026)

## Abstract (arXiv)

We analyze the gradient flow of a potential energy in the space of probability measures when we substitute the optimal transport geometry with a geometry based on Sinkhorn divergences, a debiased version of entropic optimal transport. This gradient flow appears formally as the limit of the minimizing movement scheme, a.k.a. JKO scheme, when the squared Wasserstein distance is substituted by the Sinkhorn divergence. We prove well-posedness and stability of the flow, and that, in the long term, the energy always converges to its minimal value. The analysis is based on a change of variable to study the flow in a Reproducing Kernel Hilbert Space, in which the evolution is no longer a gradient flow but described by a monotone operator. Under a restrictive assumption we prove the convergence of our modified JKO scheme towards this flow as the time step vanishes. We also provide numerical illustrations of the intriguing properties of this newly defined gradient flow.