Metraipolis › archive › dc_666be6fd91cf

Nonparametric Regression on Fixed-Cardinality Subsets:Minimax Risk and Random-Design Effects — arXiv:2609.15592

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15592
License (as archived)
CC0-1.0
Archived
2026-10-16T01:11:49.433Z
SHA-256 of the archived text
86bf385a0263ebb0169d9dbe237529e2917823f7bcb5ef1476a3a7b8f2b9a40d
Stable URL of this page
https://metraipolis.com/documento/dc_666be6fd91cf

How to cite

Nonparametric Regression on Fixed-Cardinality Subsets:Minimax Risk and Random-Design Effects — arXiv:2609.15592 — arXiv (en), https://arxiv.org/abs/2609.15592 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_666be6fd91cf (Metraipolis archive dc_666be6fd91cf, sha256 86bf385a0263ebb0169d9dbe237529e2917823f7bcb5ef1476a3a7b8f2b9a40d)
BibTeX
@misc{dc666be6fd91cf,
  title = {Nonparametric Regression on Fixed-Cardinality Subsets:Minimax Risk and Random-Design Effects — arXiv:2609.15592},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15592},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_666be6fd91cf; sha256 86bf385a0263ebb0169d9dbe237529e2917823f7bcb5ef1476a3a7b8f2b9a40d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15592. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study regression with subsets as covariates. The response is an unknown function of the input subset, and observations consist of noisy evaluations at uniformly sampled subsets, each containing exactly \(k\) items from a ground set of size \(d\). This problem arises in combination screening, bundle preference modeling, and other settings in which outcomes depend on collections of prescribed size. The fixed-cardinality constraint couples the membership coordinates, so standard product-domain notions of interaction and smoothness cannot be imported unchanged. We use the harmonic decomposition of the Johnson graph to define an intrinsic Johnson--Sobolev scale and determine the exact dimensions of low-order interaction spaces. We derive finite-sample risk bounds for harmonic projection and establish a nonasymptotic minimax characterization when the Johnson--Sobolev energy budget is controlled relative to the noise variance. We also show that stable least squares removes the signal-dependent fluctuation of empirical projection when the empirical Gram matrix is sufficiently well conditioned. For arbitrary signal-to-noise ratios, a rank-deficiency analysis quantifies the components left unidentified by the random design. Together, the rank-deficiency analysis and a centered completion estimator yield minimax bounds that match up to constants whenever \(\min(k,d-k)\) and the smoothness order are fixed. Numerical experiments reported in the Supplementary Material illustrate estimation under different interaction profiles and distinguish the effects of observation noise, random-design fluctuation, and incomplete coverage.

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/2609.15592 — 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 2026-10-16T00:31:08.664Z 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).