Skip to content
Preprint

Entropic optimal transport need not select a zero-temperature limit

Jul 2026 · 0 citations · 22 references
Mathematics

Abstract

We construct a compact metric space with an atomless probability measure and a bounded Lipschitz cost for which the entropic optimal-transport minimisers have no zero-temperature weak limit. More precisely, $P_\varepsilon$ does not converge as $\varepsilon\downarrow0$. In the example, every unregularised minimiser is singular with respect to $\mu\otimes\mu$, so that the entropy on the optimal face is identically $+\infty$. We describe the cluster set by \[ \operatorname{Clust}(P_\varepsilon)=\{P_w:w\in\mathcal W\}, \] where $P_w$ is the mixture of the two zero-cost graph couplings with weight $w$, and where $\mathcal W\subset[0,1]$ is a non-degenerate compact interval. We then compute two explicit points $w^-<w^+$ in this interval. This shows that compactness, atomlessness, and Lipschitz regularity of the cost do not imply zero-temperature convergence. We also present a compactness theorem for the general problem. If $C\in L^1(\mu\otimes\nu)$ is continuous and bounded from below on Polish spaces, then the zero-temperature cluster set is a nonempty weakly compact connected subset of the optimal face. In the proof, we apply the cluster-point theorem of Bernton, Ghosal, and Nutz and the continuity of $\varepsilon\mapsto\pi_\varepsilon$. Finally, we give local and exterior first-order criteria for full convergence and cluster membership. We show that nonconvergence is possible, but only through a connected continuum of optimal plans.

View source

Similar papers

Preprint Sep 2026

Joint Lower Bounds for Zeroth-Order Nonconvex Optimization on Euclidean Balls

We prove a joint stochastic zeroth-order lower bound for Goldstein stationarity on a Euclidean query ball, even when the ball is guaranteed to contain a stationary point. In dimension $d$, let $f=\mathbb{E}[F(\cdot;\xi)]$, assume $\mathbb{E}[\operatorname{Lip}(F(\cdot;\xi))^2]\le L_0^2$, and bound the initial objective...

Hai-Han Zhang, Wen-Dao Wu, Chen-Heng Zhang et al. · 2 citations · ⚡1
#machine learning Preprint Sep 2026

Oracle Complexity of Stochastic Fixed-Point Equations with Nonexpansive Maps

The lower bound holds against any randomized algorithm that succeeds with constant probability and extends to settings with ``sparse''noise, ruling out the possibility of improving oracle complexity as a function of $\varepsilon$ by measuring variance in a non-matching $\ell_p$ norm.

Jelena Diakonikolas, Cristóbal Guzmán, David Martínez-Rubio · 0 citations
Preprint Aug 2026

Wavelength-scale optional stopping, critical Feynman-Kac gauges, and capacitary spectral inequalities

We develop two Brownian stopping methods: one uses hitting probabilities and capacity, the other moments of weighted exit distributions. On a closed $m$-dimensional Riemannian manifold, $m\geq 2$, the first gives low-energy spectral inequalities for equilibrium measures supported on sets of zero volume. Combining scale...

Mayukh Mukherjee · 0 citations
Preprint Sep 2026

Diffusion Approximations to Schr\"{o}dinger Bridges and the Convergence of Entropic Potentials

Consider the Monge-Kantorovich optimal transport problem between two Euclidean densities $\mu$ and $\nu$ and quadratic cost. The $\varepsilon$-Schr\"{o}dinger bridge is the solution to the entropic regularized problem with regularization parameter $\varepsilon$. By taking the conditional expectation of the second coord...

G. Mulcahy, Soumik Pal · 0 citations
Preprint Sep 2026

Gromov-compactifiability of Wasserstein spaces

We characterize Gromov-compactifiability of Wasserstein spaces over Polish metric spaces for $1\leq p\leq\infty$. The space $\mathcal{P}_1(X)$ is Gromov-compactifiable if and only if $X$ is bounded and Gromov-compactifiable, whereas $\mathcal{P}_p(X)$ is Gromov-compactifiable for every $1<p<\infty$. At the other endpoi...

Hua-Jian Jiang, Zhi-Xiang Zhu · 0 citations
Preprint Aug 2026

Critical Sobolev thresholds for openness and discreteness of Monge-Ampere gradient mappings

Let $\Omega\subset\R^n$ be a domain and let $u\in W^{2,n}_{\loc}(\Omega)$ satisfy \[ \det D^2u\geq\delta>0\qquad\text{a.e. in }\Omega. \] Guerra and Tione asked whether the gradient mapping $Du$ must be open and discrete. We give a negative answer in every dimension $n\geq4$, in a form that isolates the sharp regularit...

De-Guang Zhong · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.