Wasserstein gradient flows of Maximum Mean Discrepancy with energy kernels

We study the Wasserstein gradient flow of the squared Maximum Mean Discrepancy (MMD) generated by the nonsmooth energy kernels $K(z)=-|z|^q$, $0<q<2$. In dimensions $d\ge2$, the corresponding energies are not displacement semiconvex, so standard Wasserstein-gradient-flow theory does not apply. When $d+q-2>0$, we prove global well-posedness on $\mathbb{R}^d$ for probability densities in subcritical $L^p$ spaces, with targets in the same integrability class and with finite moments. We also include the one-dimensional Coulomb endpoint $d=q=1$. For the associated $N$-particle system, we prove global noncollision and fixed-$N$ convergence to the collision-free critical set, a particle-to-continuum criticality principle, and a modulated-energy mean-field estimate that yields convergence of the particle dynamics to the continuum flow as $N\to\infty$ on every finite time interval. We also construct collision-free saddle equilibria, showing that deterministic particle trajectories need not approach global empirical minimizers. For $1\le q<2$, every continuum solution in our class has a narrowly relatively compact orbit, every $ω$-limit point is Lagrangian critical, and the orbit approaches the Lagrangian critical set. For $0<q<1$, the same conclusions hold under uniform-in-time moment and subcritical $L^p$ bounds. We prove that an absolutely continuous Lagrangian critical point equals the target when the source and target have finite moments of order $q$, except when $0<q<1$ and $d\in\{1,3\}$. Under the preceding uniform bounds, rigidity gives convergence of the continuum flow to the target throughout the rigid part of the well-posedness range. Finally, we show that no initial-data-independent multiplicative MMD decay modulus exists on $\mathbb{R}^d$, and that global Polyak--Łojasiewicz inequalities fail in several whole-space and periodic Riesz/Coulomb regimes.

Wasserstein gradient flows for Coulomb discrepancies

We study the long-time behavior of the Wasserstein gradient flow of the squared Maximum Mean Discrepancy (MMD) between a probability measure $ρ$ and a target measure $μ$, where the underlying kernel is given by a Coulomb potential. First, we establish the existence of global weak solutions starting from arbitrary Borel probability measures and prove an ultracontractive estimate, showing that the density $ρ_t$ becomes instantly bounded in $L^\infty$ for $t>0$. We also investigate the regularity of these solutions, showing that the Hölder norm can grow exponentially in time. Second, on the flat torus $\mathbb T^\mathsf{d}$, we prove exponential decay of the squared MMD along the flow toward a uniformly positive target $μ$, without requiring a lower bound on the initial data. This result is based on a ''defective Polyak-Lojasiewicz (PL) inequality'' whose defect term accounts for possible vacuum regions in the evolving density. We also prove that the usual PL inequality may fail when the target vanishes only at one point, and, in dimensions at least two, that no coercivity constant can depend only on a prescribed positive lower bound for the target. Finally, on $\mathbb R^\mathsf{d}$, we identify an obstruction at spatial infinity. For a compactly supported target, uniformly localized sources initially separated from the target by distance $D$ retain a fixed fraction of their initial squared MMD for times of order $D$. Consequently, neither a multiplicative squared-MMD decay modulus uniform over the initial datum nor a global PL inequality can hold on the unrestricted whole-space class. By contrast, under radial symmetry, source-support inclusion, and target-positivity assumptions, we establish a PL inequality and exponential convergence.

Phase transitions for the noisy transformer model in arbitrary dimension

We study the McKean--Vlasov free energy on the unit sphere associated with the unnormalized self-attention (USA) model for noisy transformer dynamics. We prove a sharp global-minimizer dichotomy in every dimension $d\ge2$. There is a unique $β_*^{(d)}>0$ such that \begin{equation*} \frac{I_{d/2+1}(β_*^{(d)})}{I_{d/2}(β_*^{(d)})}=\frac1d, \end{equation*} where $I_ν$ is the modified Bessel function of the first kind. For $0<β\le β_*^{(d)}$, the uniform density remains the unique global minimizer up to the linear-stability threshold \begin{equation*} K_\#^{(d)}(β)=\frac{β^{d/2}}{2^{d/2}Γ(d/2)I_{d/2}(β)}, \end{equation*} and the phase transition is continuous. For $β>β_*^{(d)}$, the uniform density is not globally minimizing at $K_\#^{(d)}(β)$, so the critical coupling satisfies $K_c<K_\#^{(d)}(β)$ and the transition is discontinuous. This result generalizes the authors' recent $d=2$ work arXiv:2604.16288 to arbitrary dimension. The proof uses the sharp Beckner--Onofri/logarithmic Hardy-Littlewood-Sobolev (HLS) inequality on the sphere, together with a Funk--Hecke/Bessel coefficient computation and a degree-two quartic obstruction.