Metraipolis › archive › dc_e6acaeeb68ac
Double Descent for Random Fourier Series Models — arXiv:2609.30338
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30338
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:57:07.801Z
- SHA-256 of the archived text
af1f60fdfbce14325207dd2e681f87be9578df4f8392d18f9985d5d9a18b9672- Stable URL of this page
https://metraipolis.com/documento/dc_e6acaeeb68ac
How to cite
Double Descent for Random Fourier Series Models — arXiv:2609.30338 — arXiv (en), https://arxiv.org/abs/2609.30338 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6acaeeb68ac (Metraipolis archive dc_e6acaeeb68ac, sha256 af1f60fdfbce14325207dd2e681f87be9578df4f8392d18f9985d5d9a18b9672)
BibTeX
@misc{dce6acaeeb68ac,
title = {Double Descent for Random Fourier Series Models — arXiv:2609.30338},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30338},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6acaeeb68ac; sha256 af1f60fdfbce14325207dd2e681f87be9578df4f8392d18f9985d5d9a18b9672},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30338. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We investigate the least squares linear regression problem with random partial Discrete Fourier Transform (DFT) matrices, providing a rigorous analysis of the model's generalization error. By leveraging tools from random matrix theory, we derive exact non-asymptotic bounds for the risk of the Moore-Penrose estimator, which hold for finite-dimensional problems and reveal the precise dependence on key parameters such as the sample size, dimension, and noise variance. Then we obtain a characterization of the double descent phenomenon in the linear regression context, demonstrating how the risk evolves when the number of parameters $p$ and the number of samples $n$ tend to infinity, with $p/n$ fixed. The analysis relies on applications of the Stieltjes transform for random Fourier matrices, enabling a precise description of the spectral properties of these matrices and their impact on regression performance. To validate our theoretical findings, we present several numerical examples that illustrate the double descent curves. These simulations align closely with our derived bounds, confirming their predictive power in both under-parameterized and over-parameterized regimes. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-28 in math.ST). Categorie arXiv: Statistics Theory (math.ST) ; Information Theory (cs.IT). Pagina del lavoro: https://arxiv.org/abs/2609.30338 — 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 2026-10-08T02:26:58.152Z dalla pagina https://arxiv.org/catchup/math.ST/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).