AI & ML
Sharp conditioning and quantitative stability of optimal transport
arXiv cs.NA0 views
arXiv:2610.07577v1 Announce Type: cross Abstract: When a feasible plan is obtained whose quadratic transport cost is known to be close to the optimal cost, we try to determine how close the feasible plan is to the true optimal map under mild density and moment conditions. The source and target may be unbounded or have non-compact supports. We show that for a source with density in $L^p$ and an $n$-th moment, let $s=1-1/p$ and $\eta=sn/[n+(d-1)s]$. Under the target constraint $\int |y|^m[\log(e+|y|)]^\beta\,d\nu\leqslant1$, the worst-case class-uniform conditioning has a sharp modulus comparable to \[ t^{\eta(m-2)/[m(1+\eta)-\eta]} [\log(e/t)]^{-\beta(2+\eta)/[m(1+\eta)-\eta]}, \] whenever $t>0$ is small. This holds for $m\geqslant2$ and $\beta\geqslant0$. When $m=2$, every $\beta>0$ gives a sharp logarithmic modulus, whereas the $m=2,\,\beta=0$ extreme has no vanishing modulus. The matching lower bound is verified for both the squared map error and barycentric projection error. The sharp map error bounds allow us to directly derive quantitative stabilities of common source Brenier maps without passing through potential estimates, thereby avoiding loss of information. These stabilities strictly improve the corresponding results of Delalande-Merigot \cite{delalande2023quantitative} and Letrouit-M\'erigot \cite{letrouit2026gluing} under identical or weaker settings, particularly no convexity of the source support or bounds of the source density are assumed.
Source:https://arxiv.org/abs/2610.07577PreviousWell-posed by Design: Learning Constitutive Laws from Velocity Data using Convex Neural Network PotentialsNextLearning PDE solution operators with variable initial conditions via Latent Dynamics Networks
Related posts
7.9% to 48.1%: LLM rewrote Qwen weights, no training
0dev.to
Spousal Open Work Permits in Canada: Who Qualifies in 2026 and What to Prepare
0dev.to
Reading ingredient lists from phone photos: a crop bug, a model bench, and why the AI never gives the verdict
0dev.to
Edital exige guardrail
0dev.to
Convert an SVG to a PNG in the Browser, Without Uploading the File
0dev.to
Generative Simulation Benchmarking for planetary geology survey missions for extreme data sparsity scenarios
0dev.to