Answers are grounded in this paper and cite their sources.
We study empirical convergence rates for $(p,q)$-Gromov-Wasserstein (GW) distances Dp,q for arbitrary real exponents $p>0$ and q≥1. Let $μ$ and $ν$ be probability measures on compact metric spaces X and Y, and let μₙ and νₘ be their empirical measures, constructed from independent i.i.d. samples of sizes n and m. If the spaces X,\,Y are compact subsets of the Euclidean spaces Rdₓ and Rdy, respectively, we obtain an upper bound of order (n m)-(p2)/((dₓ dy) 2(p2)) on the plug-in error of Dp,qᵖ(μₙ,νₘ) in expectation, up to a logarithmic factor at the critical dimension dₓ dy=2(p2). On Euclidean balls, this rate is sharp up to the logarithmic factor. More generally, we show that the same upper bound holds when one space is a compact subset of a complete, connected d-dimensional Riemannian manifold and the other has polynomial covering numbers, with dₓ dy replaced by d. Earlier works on $(2,2)$-GW, $(2,1)$-GW and other even-order cases rely on variational representations of GW distances that are specific to their exponents. We instead reduce the plug-in error to an analysis of empirical processes through local duality, which may be of independent interest.
No takes yet. Share an insight, caveat, or question.
Leung et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: