Metraipolis › archive › dc_20eb935f045a

Sieve-free ReLU Bayesian priors with near-minimax posterior contraction — arXiv:2610.23308

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23308
License (as archived)
CC0-1.0
Archived
2026-10-19T09:37:53.247Z
SHA-256 of the archived text
e79966c541b405a7d84b7b5be085a5974e26b1ad79d95140ff21279f4ac0e47d
Stable URL of this page
https://metraipolis.com/documento/dc_20eb935f045a

How to cite

Sieve-free ReLU Bayesian priors with near-minimax posterior contraction — arXiv:2610.23308 — arXiv (en), https://arxiv.org/abs/2610.23308 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20eb935f045a (Metraipolis archive dc_20eb935f045a, sha256 e79966c541b405a7d84b7b5be085a5974e26b1ad79d95140ff21279f4ac0e47d)
BibTeX
@misc{dc20eb935f045a,
  title = {Sieve-free ReLU Bayesian priors with near-minimax posterior contraction — arXiv:2610.23308},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23308},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20eb935f045a; sha256 e79966c541b405a7d84b7b5be085a5974e26b1ad79d95140ff21279f4ac0e47d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23308. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We establish fractional-posterior contraction for shallow ReLU networks in Gaussian random-design regression with a $\beta$-Hölder target, using priors independent of the sample size and smoothness parameters. For any fixed design law $P_X$ on $[0,1]^d$, we obtain contraction in Rényi divergence and, after clipping posterior draws at a bound on the target range, in squared $\mathcal{L}^2(P_X)$ loss at rate $(\log n/n)^{2\beta/(2\beta+d)}$. This matches the classical Hölder minimax rate up to a logarithmic factor. These priors have random finite width and use width-dependent uniform or Gaussian weight distributions, or width-independent Student $t$ distributions, including Cauchy distributions.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.ST, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2610.23308 — 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 2026-10-19T09:33:59.706Z dalla pagina https://arxiv.org/list/math.ST/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).