Necessary and sufficient conditions for convergence of low-intensity Poisson–Voronoi diagrams to a unique ideal tessellation, applied to symmetric spaces and Diestel–Leader graphs.
Mixed citations
Grundlehren der mathematischen Wissenschaften [Fun- damental Principles of Mathematical Sciences], vol
Mixed citation behavior. Most common role is background (60%).
40
Pith papers citing it
3,292
external citations · Crossref
Background
60% of classified citations
citation-role summary
background 3
dataset 1
method 1
citation-polarity summary
representative citing papers
Function graph transformers use graph measures to provide a measure-theoretic framework where standard transformer components universally approximate operators between function spaces while preserving single-valued function outputs.
Introduces structured DRO for learned inverse problem reconstructions with ambiguity sets aligned to the forward operator, yielding explicit dual representations and a worst-case bound that induces Tikhonov regularization on the operator Lipschitz constant.
The authors construct a Mortensen-type observer on the Wasserstein space P2(R^d), establish dynamic programming and viscosity solution properties for the associated HJB equation using two formulations, prove uniqueness via comparison, and introduce a convergent semi-Lagrangian scheme.
Introduces tangential Bayes denoiser for Riemannian Gaussian mixtures on manifolds via spectral Laplace-Beltrami approximation, with nearly Bayes risk in low noise and minimax optimality on the circle.
Derivation of a stochastic maximum principle for McKean-Vlasov SDEs with common noise that requires a third adjoint state to linearize all second-order terms in the cost expansion.
Attention in minimal transformers under corruption performs in-context empirical Bayes via a single kernel-weighted posterior mean step followed by depth-driven particle dynamics refinement.
CausalHealth detects lithium-ion battery degradation with 100% sensitivity and up to 402-cycle lead time using causal anomaly scores from voltage, current, temperature, and resistance time series across seven cells.
Presents a likelihood-free transport map learned by minimizing an averaged energy-distance objective to amortize Bayesian inference for inverse problems, including PDE-constrained cases with neural operator representations.
Primitive sequences obtained from iterated antiderivatives of the CDF are homeomorphic to probability measures on compact intervals, equivalent to factorial-rescaled moments of the reflected variable, and yield sharp bounds on functionals when the first m terms are fixed.
A Deep Set encoder plus normalizing flow model trained on five million CRPropa 3 events recovers UHECR source parameters without bias and classifies primary composition at over 98 percent accuracy.
Derives Õ(d β² A² / ε⁴) oracle complexity for AIS estimating normalizing constant Z to relative error ε and introduces reverse diffusion sampler for geometric paths with large action.
Derives adaptive generalization bounds {c_m / N^{1/(2∨m)}} for digital ML models via new concentration of measure results on finite metric spaces, with c_m = O(sqrt(m)).
A Minkowski-type Wasserstein framework for location-scale mixtures reduces multimarginal OT to discrete component transport with linear complexity and shows competitive domain adaptation performance.
GalSBI extended with optimal transport subhalo matching and SBI to forward-model galaxy population plus clustering, validated against DES Y3 and HSC data with public code release.
Non-closing Lie brackets of intervention-response fields can serve as a high-recall screen for causal edges under latent confounding, but do not by themselves identify general DAGs.
Proposes and analyzes a homogeneity test using squared L2 distance of empirical EOT maps to uniform-on-ball reference, with FCLT, Gaussian quadratic null limit, consistency, local power, and weighted multiplier bootstrap.
Matching in semantic SSL feature space via Sinkhorn divergence enables effective one-step generation on ImageNet by inducing compact geometry for distribution matching, with training and evaluation features best kept distinct.
Wasserstein least squares extends Euclidean least squares to distribution-valued responses via convex analysis, yielding n^{-1/2} rates under template deformation and faster barycenter rates than prior work.
Proves SLiCEs are universal time-series generators approximating path laws in W_∞ and proposes G-SLiCEs for path-space flow matching with benefits on irregular grids.
Introduces extended bridge functions and derives identification results for joint interventional distributions retaining proxy variables in proximal causal inference.
SPIN performs bidirectional domain transfer in SBI to retain parameter mutual information from unlabeled real observations, improving real-world posterior inference under increasing misspecification.
Quantitative 2-Wasserstein bounds are established between finite-width deep neural networks and their infinite-width Gaussian limits using a Lindeberg principle for successive Gaussian replacement of weights.
VSLP infers dense segmentations from global label proportions via a pre-trained transformer for initial confidence maps followed by variational optimization using Wasserstein fidelity and a learned regularizer, outperforming prior weakly supervised methods on histopathology datasets.
citing papers explorer
-
Neural Posterior Estimation for UHECR source inference from 3D propagation simulations
A Deep Set encoder plus normalizing flow model trained on five million CRPropa 3 events recovers UHECR source parameters without bias and classifies primary composition at over 98 percent accuracy.