Metraipolis › archive › dc_07bb756fb88b

Dimension Changes the Scale-Signal Channel in Nearest-Neighbor Two-Sample Testing — arXiv:2610.41271

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41271
License (as archived)
CC0-1.0
Archived
2026-11-03T08:16:48.883Z
SHA-256 of the archived text
f1e8e057541fc6e515de422c0ddf3b52ad6b04df8083b5bad746a32217e72795
Stable URL of this page
https://metraipolis.com/documento/dc_07bb756fb88b

How to cite

Dimension Changes the Scale-Signal Channel in Nearest-Neighbor Two-Sample Testing — arXiv:2610.41271 — arXiv (en), https://arxiv.org/abs/2610.41271 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07bb756fb88b (Metraipolis archive dc_07bb756fb88b, sha256 f1e8e057541fc6e515de422c0ddf3b52ad6b04df8083b5bad746a32217e72795)
BibTeX
@misc{dc07bb756fb88b,
  title = {Dimension Changes the Scale-Signal Channel in Nearest-Neighbor Two-Sample Testing — arXiv:2610.41271},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41271},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07bb756fb88b; sha256 f1e8e057541fc6e515de422c0ddf3b52ad6b04df8083b5bad746a32217e72795},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41271. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Nearest-neighbor two-sample tests are often analyzed with dimension fixed. We study the power of the generalized edge-count test on a directed 1-nearest-neighbor graph. This statistic combines a weighted sum and a difference of the two within-sample edge counts. For balanced isotropic Gaussian samples with $d/\log N\to\gamma>0$, we derive the connection probabilities under local location and scale alternatives. Under location alternatives, the two counts have equal mean shifts, which cancel in their difference. Under scale alternatives, the two counts instead have mean shifts of opposite signs. We also derive the growth rate of the null expectation $\mathbb{E}_0C_3$, where $C_3$ counts pairs of directed edges sharing exactly one vertex. On an explicit range of $\gamma$, we establish local-power limits strictly above the test level for scale alternatives in the difference component at the scale $|\varepsilon_N|\asymp (\mathbb{E}_0C_3)^{1/2}/(Nd)$. Here $\mathbb{E}_0C_3$ gives the variance order of the difference count under these local alternatives. At this scale, the standardized drift of the weighted sum vanishes. When $d=1$, the weighted component instead detects local Gaussian scale alternatives while the difference component has no limiting drift. Thus dimension changes both the magnitude of a detectable scale difference and the component of the test that detects it.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.ST, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2610.41271 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T08:04:38.758Z dalla pagina https://arxiv.org/list/math.ST/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).