Metraipolis › archive › dc_77e8b58bbaf1

PTNO: Training Neural Operators with Noisy Monte Carlo Estimates for Particle Transport Problems — arXiv:2609.40090

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40090
License (as archived)
CC0-1.0
Archived
2026-10-07T12:43:05.730Z
SHA-256 of the archived text
ca7b8105cb2b96c04cc502d99ea9a41ca782399884d68fe4f2b233e4717cda96
Stable URL of this page
https://metraipolis.com/documento/dc_77e8b58bbaf1

How to cite

PTNO: Training Neural Operators with Noisy Monte Carlo Estimates for Particle Transport Problems — arXiv:2609.40090 — arXiv (en), https://arxiv.org/abs/2609.40090 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_77e8b58bbaf1 (Metraipolis archive dc_77e8b58bbaf1, sha256 ca7b8105cb2b96c04cc502d99ea9a41ca782399884d68fe4f2b233e4717cda96)
BibTeX
@misc{dc77e8b58bbaf1,
  title = {PTNO: Training Neural Operators with Noisy Monte Carlo Estimates for Particle Transport Problems — arXiv:2609.40090},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40090},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_77e8b58bbaf1; sha256 ca7b8105cb2b96c04cc502d99ea9a41ca782399884d68fe4f2b233e4717cda96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40090. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Particle transport under multiple scattering is central to radiative transfer and plasma physics, yet high-fidelity Monte Carlo (MC) simulations must trace prohibitively many particles. Learning-based surrogates can amortize this cost, but typically train on expensive, well-converged MC solutions. We propose the Particle Transport Neural Operator (PTNO), a neural operator that learns particle transport surrogates directly from noisy, low-cost MC labels. Such labels pose two challenges: (1) high variance, which destabilizes standard supervised learning, and (2) a high dynamic range (HDR) spanning many orders of magnitude. For the first, we learn the solution operator from noisy labels of many configurations, amortizing MC cost and generalizing to unseen configurations. Because MC labels are unbiased, we show that the squared loss on them shares its minimizer with the loss on converged solutions, and our budget-allocation study over training scenes $M$, MC samples per render $N$, and independent renders per scene $K$ shows that many noisy scenes beat fewer converged ones. For the second, a nonlinear transform such as the logarithm biases noisy supervision. Instead, PTNO keeps labels in physical space and enforces positivity with a softplus output layer that represents small values effectively. We further train with a pointwise relative $L_2$ loss (PRelL2), the stop-gradient relative loss of HDR denoising and neural rendering, which normalizes each residual by the stop-gradient prediction instead of the noisy label. We demonstrate PTNO on neutron transport in fusion reactors and radiative transfer in participating media. On the two neutronics tasks, PTNO is $10^4$-$10^5\times$ faster than converged MC on the same CPU and $10^3$-$10^5\times$ cheaper than MC at matched accuracy; on the two radiative-transfer tasks, MC at matched accuracy costs $0.8$-$11\times$ as much as PTNO.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.40090 — 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 2026-10-07T12:14:13.810Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).