stat.MLAug 2, 2026

How fine a change can moments see? A scale law for detecting distribution shift, with a kernel calibration rule

Authors: Adel Kaleche

Organizations: Independent researcher, France

Abstract

Detecting that a stream of high-dimensional embeddings has changed is usually framed as a choice of statistic. We give a scale law that constrains any moment-based choice and test it against topological alternatives. The law: certifying a feature of spatial scale eps carrying mass fraction f requires polynomial tests of degree N* >= log(1/f)/(2 eps), proved via the Chebyshev extremal problem; a Gauss-quadrature construction gives N* >= 4b-1 for a b-scale topology, so cost is set by feature fineness, not feature count. The law is one-sided: we exhibit an annulus whose mean, covariance and all fourth-order moments equal those of a filled disk, yet H_1 is nonzero. Its practical content is a calibration rule. The upper bound is attained by Gaussian test functions, the RKHS witness of an RBF kernel, so the law predicts which bandwidth an MMD test should use: the feature scale. On real embedding streams we measure sigma*/eps with median 1.12 (IQR 1.01-1.52, n=26) over three settings and three scales, and a data-driven bandwidth reaches AUC >= 0.95. Against an adversary optimised against the defender's statistics (mean, covariance, k-NN, kurtosis), only a bandwidth-matched kernel test still detects. For persistent homology the verdict is mixed and depends on choices usually left implicit. The summary matters more than the filtration: total persistence attains recall 0.75 at FPR 1% where the first persistence landscape attains 0.00. What survives is a cost gap, not a power gap: where persistence works it costs 116x kurtosis, which works at least as well. We conclude not that topological summaries are useless, but that on this task a kernel test whose bandwidth the law sets dominates them.

Explore similar work

CardsList
Sep 14, 2026cs.CG

Low-Dimensional Embeddings for Gaussian Kernels on Manifolds

The Gaussian kernel is a widely used similarity measure underlying kernel methods such as kernel PCA and spectral clustering, but computing Gaussian kernel distances for many pairs of points can be expensive. Using Random Fourier Features (RFF), Chen and Phillips [ALT 2017] showed that for points in a dd-dimensional Euclidean ball in RN{\mathbb R}^N, t=Ω((d/ε2)log⁡(dR/ε))t=Ω((d/\varepsilon^2)\log(dR/\varepsilon)) features suffice to preserve all pairwise Gaussian kernel distances within a (1±ε)(1\pm\varepsilon) factor with high probability. We establish a uniform relative-error embedding theorem for the more general setting of an arbitrary positive-reach submanifold M⊂RN\mathcal M\subset{\mathbb R}^N of intrinsic dimension dd. We show that t=O((d/ε2)log⁡(vol⁡(M)2N2d/(vol⁡(B1d(0))2rch⁡(M)2dε2d+1δ)))t=O((d/\varepsilon^2)\log(\operatorname{vol}(\mathcal M)^2N^{2d}/(\operatorname{vol}(B_1^d(0))^2\operatorname{rch}(\mathcal M)^{2d}\varepsilon^{2d+1}δ))), or approximately O((d2/ε2)(log⁡N+log⁡(1/(εδ))))O((d^2/\varepsilon^2)(\log N+\log(1/(\varepsilonδ)))), RFFs suffice, with probability 1−δ1-δ, to preserve the Gaussian kernel distance between every pair of manifold points up to relative error ε\varepsilon. Thus the bound depends only logarithmically on the ambient dimension and on manifold parameters such as volume and reach, while retaining the 1/ε21/\varepsilon^2 Euclidean rate. We also prove a topological consequence: under the same RFF embedding, persistent homology is preserved in the sense that weighted Cech and Rips filtrations built from Gaussian kernel power distance are (1±ε⋆)(1\pm\varepsilon_\star)-interleaved, where ε⋆\varepsilon_\star accounts for both distance distortion and kernel-weight approximation.
Soumik Dutta, Kunal Dutta
Topic pending
AskPDF
Jul 27, 2026stat.ML

Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD

Over the past 20 years, kernel discrepancies have been leveraged as a highly powerful tool for quantifying the disagreement of distributions, with numerous successful applications in two-sample, goodness-of-fit, and independence testing, among others. Their fastest estimators are known to converge at a parametric rate---n−1/2n^{-1/2}---under mild conditions. While this rate is known to be minimax optimal on Rd\mathbb R^d under strict assumptions with bounded kernels, little is known about its optimality beyond the finite-dimensional Euclidean setting with unbounded kernels. In this work, we prove that the minimax lower bound of estimation of the most popular kernel discrepancies (maximum mean discrepancy, Hilbert-Schmidt independence criterion and kernel Stein discrepancy; MMD, HSIC, KSD) is n−1/2n^{-1/2} on general topological spaces, and under mild assumptions on the kernel; the same rates are shown (as corollaries) to hold for the estimation of the mean embedding and the centered cross-covariance operator. Our results settle the question of optimal estimation of these kernel discrepancies.
Jose Cribeiro-Ramallo, Florian Kalinke, Zoltán Szabó
Maximum Mean DiscrepancyKernel Hilbert SpacesConcentration InequalitiesEstimatorsCovariance EstimationLower Bounds
AskPDF
Feb 8, 2026stat.ML

Persistent Entropy as a Detector of Phase Transitions

Persistent entropy is a scalar summary of persistence barcodes widely used to detect regime changes, yet there is no account of when a structural change in a barcode must produce a detectable change in entropy. We establish a model-agnostic theorem supplying such conditions. Treating persistence diagrams as random objects indexed by a control parameter, we identify a dispersion-condensation mechanism in the normalized persistence weights and derive an explicit lower bound on the entropy difference between the two regimes, valid with high probability at finite sample size and insensitive to the absolute scale of bar lifetimes. We also give a procedure for verifying the hypotheses on empirical barcodes. Applied to convolutional networks, the criterion shows that the circular organization of learned filters reported by Gabrielsson and Carlsson emerges through a sharp topological phase transition, and locates its onset: within a few hundred iterations on MNIST, but an order of magnitude later on CIFAR-10. The same criterion detects the Kuramoto synchronization and Vicsek order-disorder transitions.
Marcos Gutierrez-del-Pozo, Eduardo Paluzo-Hidalgo, Matteo Rucco
Phase TransitionsChange-Point DetectionPersistent HomologyTransitionsDistributional SignaturesConvolutional Neural Networks
AskPDF