Metraipolis › archive › dc_69b72e11e808

Residual neural networks overcome the curse of dimensionality for semilinear heat equations — arXiv:2609.03626

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03626
License (as archived)
CC0-1.0
Archived
2026-10-17T02:08:40.542Z
SHA-256 of the archived text
a766833468b9b203bc7604a0ed3455fda982cb7d1f6256359b4257c08a916f8a
Stable URL of this page
https://metraipolis.com/documento/dc_69b72e11e808

How to cite

Residual neural networks overcome the curse of dimensionality for semilinear heat equations — arXiv:2609.03626 — arXiv (en), https://arxiv.org/abs/2609.03626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69b72e11e808 (Metraipolis archive dc_69b72e11e808, sha256 a766833468b9b203bc7604a0ed3455fda982cb7d1f6256359b4257c08a916f8a)
BibTeX
@misc{dc69b72e11e808,
  title = {Residual neural networks overcome the curse of dimensionality for semilinear heat equations — arXiv:2609.03626},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03626},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69b72e11e808; sha256 a766833468b9b203bc7604a0ed3455fda982cb7d1f6256359b4257c08a916f8a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Rigorous results show that feedforward neural networks can overcome the curse of dimensionality in the numerical approximation of high-dimensional partial differential equations (PDEs), but comparatively little is known about residual neural networks (ResNets) in the nonlinear PDE setting. We prove that ResNets overcome the curse of dimensionality in the numerical approximation of solutions of semilinear heat equations with globally Lipschitz continuous, gradient-independent nonlinearities: under polynomial growth and network approximability hypotheses on the PDE data, there exist $\eta\in(0,\infty)$ and ResNets $\Psi_{d,\varepsilon}$, $d\in\mathbb{N}$, $\varepsilon\in(0,1]$, with at most $\eta d^{\eta}\varepsilon^{-\eta}$ parameters whose realizations approximate the solution in dimension $d$ with an $L^2$-error of at most $\varepsilon$. The proof represents one deterministic realization of a multilevel Picard estimator by a ResNet whose shortcut connections transmit the spatial variable and a scalar accumulator, while the residual branches successively add the summands of the estimator. For ridge-sum initial conditions, admissible sigmoidal activations, and globally Lipschitz truncations of the nonlinearity, we obtain, for every $\xi>0$, the explicit bound $C_\xi d^{4+\xi}\varepsilon^{-(3+\xi)}$ on the number of parameters.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG); Analysis of PDEs (math.AP); Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2609.03626 — 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 2026-10-17T01:47:25.627Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).