Metraipolis › archive › dc_2a95f8fc47ce

Toscani-Fourier Distance on Probability Measures: Wasserstein Control, Topological Equivalence on Model Classes, and Duality — arXiv:2609.23163

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23163
License (as archived)
CC0-1.0
Archived
2026-10-09T07:08:24.389Z
SHA-256 of the archived text
2b1edc034dbd414759b64101011e7bd9abe0bd7969745ae7f36be5d94d04c6f2
Stable URL of this page
https://metraipolis.com/documento/dc_2a95f8fc47ce

How to cite

Toscani-Fourier Distance on Probability Measures: Wasserstein Control, Topological Equivalence on Model Classes, and Duality — arXiv:2609.23163 — arXiv (en), https://arxiv.org/abs/2609.23163 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a95f8fc47ce (Metraipolis archive dc_2a95f8fc47ce, sha256 2b1edc034dbd414759b64101011e7bd9abe0bd7969745ae7f36be5d94d04c6f2)
BibTeX
@misc{dc2a95f8fc47ce,
  title = {Toscani-Fourier Distance on Probability Measures: Wasserstein Control, Topological Equivalence on Model Classes, and Duality — arXiv:2609.23163},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23163},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a95f8fc47ce; sha256 2b1edc034dbd414759b64101011e7bd9abe0bd7969745ae7f36be5d94d04c6f2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23163. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Comparing probability measures in machine learning trades transport geometry against computational cost: Wasserstein distances encode the geometry of $\mathbb R^d$ but require solving a transport problem, while kernel discrepancies are cheap to evaluate yet depend delicately on their test class. We study the Toscani--Fourier family $\mathrm T_{s,p}$, the weighted $L^p$ norm of the difference of two characteristic functions, as a continuous Fourier-side discrepancy on $\mathbb R^d$. For $1\le p<\infty$ we show that $d/p<s<1+d/p$ is exactly the window in which $\mathrm T_{s,p}$ is finite on $\mathcal P_p(\mathbb R^d)$, both endpoints already failing for a pair of Dirac measures, and we establish the metric, embedding, and compactness structure of the resulting space, which we prove to be complete. Duality identifies $\mathrm T_{s,p}$ as an integral probability metric over a homogeneous Fourier--Lebesgue ball, with an explicit extremizer when $1<p<\infty$. We prove the global bound $\mathrm T_{s,p}\lesssim W_p^{\,s-d/p}$, whose exponent is sharp, show that no global converse of any form can hold, and recover topological equivalence with $W_p$ on bounded-support and uniform-tail classes, together with explicit reverse moduli on bounded-support classes that improve the imported energy-kernel exponent at $p=2$. There, $\mathrm T_{s,2}$ is a constant multiple of the classical energy distance, which yields an exact finite-sample identity for the mean of the empirical discrepancy; the numerical experiments are otherwise diagnostic.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Functional Analysis (math.FA); Probability (math.PR); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.23163 — 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 2026-10-09T06:58:09.556Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).