Metraipolis › archive › dc_9a5d70a42e9e

Resolvable Fourier Degree and Minimax Estimation on theBoolean Hypercube — arXiv:2609.15595

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15595
License (as archived)
CC0-1.0
Archived
2026-10-16T01:11:53.633Z
SHA-256 of the archived text
f37ba3c254c2b6f4bf549e5c3f61164ac58d797878abaa8e6ec221e3c6676a46
Stable URL of this page
https://metraipolis.com/documento/dc_9a5d70a42e9e

How to cite

Resolvable Fourier Degree and Minimax Estimation on theBoolean Hypercube — arXiv:2609.15595 — arXiv (en), https://arxiv.org/abs/2609.15595 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9a5d70a42e9e (Metraipolis archive dc_9a5d70a42e9e, sha256 f37ba3c254c2b6f4bf549e5c3f61164ac58d797878abaa8e6ec221e3c6676a46)
BibTeX
@misc{dc9a5d70a42e9e,
  title = {Resolvable Fourier Degree and Minimax Estimation on theBoolean Hypercube — arXiv:2609.15595},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15595},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9a5d70a42e9e; sha256 f37ba3c254c2b6f4bf549e5c3f61164ac58d797878abaa8e6ec221e3c6676a46},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15595. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study high-dimensional nonparametric regression on the Boolean hypercube \(\{0,1\}^d\), from a sample of size \(n\), under a Fourier--Sobolev budget, i.e., a bound \(B\) on the total quadratic influence of the regression function. The central object is the resolvable Fourier degree \(D^*(d,n)\), defined as the largest interaction order \(D\) such that the dimension of the degree-\(D\) Fourier--Walsh space does not exceed \(n\). We prove that the minimax risk over Fourier--Sobolev ellipsoids is of order \(B/D^*(d,n)\): estimation is possible up to the statistically visible interaction order, and the budget controls the residual mass carried by higher-order interactions. We then study monotone regression under the same budget. For monotone functions supported on a known set of \(s\) coordinates, with \(s\) of order \(\log n\), we obtain a matching minimax rate of order \(B/s\). Finally, we consider an unknown-support model in which the function is monotone and depends on at most \(s\) coordinates; its minimax risk is governed by the intrinsic dimension \(s\) together with the logarithmic cost of selecting the active support.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-15 in math.ST).
Categorie arXiv: Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.15595 — 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 2026-10-16T00:31:08.666Z dalla pagina https://arxiv.org/catchup/math.ST/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).