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

• URL: http://arxiv.org/abs/2608.01268v1
• Date: Sun, 02 Aug 2026 14:21:58 GMT
• Title: How fine a change can moments see? A scale law for detecting distribution shift, with a kernel calibration rule
• Abstract summary: We show that a kernel test whose bandwidth the law sets dominates them.<n>We conclude not that topological summaries are useless, but that on this task a kernel test whose bandwidth the law sets dominates them.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Same Flow, Different Paths: Variance Reduction in Flow Matching [67.12978375116599]
  We study the choice of this path from an optimization perspective.<n>Our main finding is that the choice of path $g_t$ can fundamentally change the convergence rate of SGD.
  arXiv  Detail & Related papers  (2026-09-15T15:01:04Z)
• Certifying bipartite entanglement on a superconducting processor from a corrected QAOA cost layer [0.0]
  We report a pre-registered single-device study on the nine-qubit superconducting processor Red at the Barcelona Supercomputing Center.<n>We certify bipartite entanglement of a corrected QAOA cost layer on the good coupler at depth one by two-qubit tomographic negativity.<n>We measure the device physics directly: in a pre-registered manipulation on a fixed Bell preparation, reducing the CZ pulse amplitude causally reduces the certified negativity.
  arXiv  Detail & Related papers  (2026-09-08T22:23:35Z)
• Constrained Online Learning with Noisy Constraint Values [55.29259818039367]
  Under common feasibility, our LEDGER algorithm attains $O(sqrt T)$ expected regret and $O(sqrtTlog(eT))$ expected budget violation.<n>Neither a Slater condition, independence between feedback channels, nor an absolute constraint-value bound is needed.
  arXiv  Detail & Related papers  (2026-09-07T01:38:41Z)
• Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection [0.0]
  Benchmark contamination is diagnosed with n-gram overlap, likelihood-based membership inference, or canary strings.<n>We show the natural way to do this does not work, specify one that survives measurement, then find that the correction making it work carries more variance than the null it is tested against.
  arXiv  Detail & Related papers  (2026-08-12T23:27:20Z)
• The Cost of Adaptivity: Matching Lower Bounds Across Learning Problems [1.0742675209112622]
  We formalize nuisance adaptation via a slice-normalized minimax ratio.<n>We also define the cost of expanding from one preannounced Gaussian query to arbitrary post-hoc inspection.
  arXiv  Detail & Related papers  (2026-08-09T17:19:11Z)
• GRACE: Gated Refinement for Accurate Causal Edge Discovery in High-Dimensional Time Series [0.0]
  Fast linear CI skeleton provides high-recall candidates.<n>A single gated model prunes false positives by learning which edges genuinely improve prediction.<n> GRACE matches or exceeds expensive nonlinear CI tests at a fraction of the cost.
  arXiv  Detail & Related papers  (2026-06-22T19:26:38Z)
• Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics [0.0]
  Detectors for radio-frequency impairments are usually reported with a single AUC measured on the distribution they were tuned on.<n>We ask whether this optimism can be predicted before any out-of-distribution data is seen.
  arXiv  Detail & Related papers  (2026-06-20T14:10:59Z)
• Scaling Laws in Linear Regression: Compute, Parameters, and Data [86.48154162485712]
  We study the theory of scaling laws in an infinite dimensional linear regression setup.<n>We show that the reducible part of the test error is $Theta(-(a-1) + N-(a-1)/a)$.<n>Our theory is consistent with the empirical neural scaling laws and verified by numerical simulation.
  arXiv  Detail & Related papers  (2024-06-12T17:53:29Z)
• A Permutation-free Kernel Two-Sample Test [45.201000620965914]
  We propose a new quadratic-time MMD test statistic based on sample-splitting and studentization.<n>For large sample sizes, our new cross-MMD provides a significant speedup over the MMD, for only a slight loss in power.
  arXiv  Detail & Related papers  (2022-11-27T18:15:52Z)
• Debiased Sinkhorn barycenters [110.79706180350507]
  Entropy regularization in optimal transport (OT) has been the driver of many recent interests for Wasserstein metrics and barycenters in machine learning. We show how this bias is tightly linked to the reference measure that defines the entropy regularizer. We propose debiased Wasserstein barycenters that preserve the best of both worlds: fast Sinkhorn-like iterations without entropy smoothing.
  arXiv  Detail & Related papers  (2020-06-03T23:06:02Z)
• Differentially Quantized Gradient Methods [53.3186247068836]
  We show that Differentially Quantized Gradient Descent (DQ-GD) attains a linear contraction factor of $maxsigma_mathrmGD, rhon 2-R$. No algorithm within a certain class can converge faster than $maxsigma_mathrmGD, 2-R$.
  arXiv  Detail & Related papers  (2020-02-06T20:40:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.