Metraipolis › archive › dc_58d90dca79f7

Two-Sample Testing via Path-based Inference — arXiv:2610.05684

Source
arXiv
Original
https://arxiv.org/abs/2610.05684
License (as archived)
CC0-1.0
Archived
2026-10-06T05:27:06.465Z
SHA-256 of the archived text
fab081ecfba4c2ced3b4892b28e0f19f01bb7f687e31fd5a275661e9e6b8a092
Stable URL of this page
https://metraipolis.com/documento/dc_58d90dca79f7

How to cite

Two-Sample Testing via Path-based Inference — arXiv:2610.05684 — arXiv, https://arxiv.org/abs/2610.05684 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58d90dca79f7 (Metraipolis archive dc_58d90dca79f7, sha256 fab081ecfba4c2ced3b4892b28e0f19f01bb7f687e31fd5a275661e9e6b8a092)
BibTeX
@misc{dc58d90dca79f7,
  title = {Two-Sample Testing via Path-based Inference — arXiv:2610.05684},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05684},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58d90dca79f7; sha256 fab081ecfba4c2ced3b4892b28e0f19f01bb7f687e31fd5a275661e9e6b8a092},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05684. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern deep generative models are primarily studied for their ability to generate realistic samples, yet the generative dynamics they learn can also serve as objects of statistical inference. We develop this idea for two-sample testing, the problem of deciding whether the same distribution generated two finite datasets. Using stochastic interpolants, we connect both distributions to a shared Gaussian bottleneck, so that each half of the resulting path is a Gaussian channel acting on a single population. We prove that the null hypothesis holds if and only if the population denoiser, or equivalently, the velocity fields of the two halves, coincide at any single noise level, which amounts to a reflection symmetry of the path about the bottleneck. Deviations from this symmetry yield a continuum of two-sample witnesses, which we estimate via held-out regression risks on learned denoisers and velocities and aggregate along the path; under an information-theoretic weighting, the aggregated discrepancy equals the Jeffreys divergence between the noise-smoothed distributions. Calibrating the resulting statistics by permutation yields tests that are valid in finite samples for any trained networks and consistent when the fields are learned accurately. On a synthetic benchmark and three image benchmarks, the proposed tests improve power over the strongest baseline by up to 33 percentage points at an equal total sample budget, with the best choice of regression representation and path weighting depending on the data modality. These results show that generative paths provide a principled representation for statistical testing, extending stochastic-interpolant models beyond generation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05684 — 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 2026-10-06T05:24:06.060Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).