arXiv AI October 1, 2026 By Yubo Cao, Xi Deng, Mengqi Xia, Vignesh Gopakumar, Ander Gray, Anima Anandkumar

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

The paper introduces PTNO, a neural operator that learns particle transport surrogates directly from noisy, low‑cost Monte Carlo (MC) labels, addressing high variance and high dynamic range challenges. By training on many noisy scenes, PTNO achieves comparable accuracy to converged MC while dramatically reducing computational cost, and it employs a softplus output and a pointwise relative L2 loss to handle HDR data. Experiments on neutron transport in fusion reactors and radiative transfer in participating media show speedups of up to 10⁵× and cost reductions of up to 10⁵× compared to traditional MC.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 28

Generative Monte Carlo Sampling for Constant-Cost Particle Transport

Generative Monte Carlo (GMC) is a new particle transport simulation method that embeds generative AI into solving the linear Boltzmann equation. By treating cell transmission as a conditional generation task, neural networks trained with conditional flow matching produce particle exit states—position, direction, and path length—without simulating scattering histories. GMC generalizes across materials using optical coordinate scaling, matches standard Monte Carlo’s statistical accuracy and convergence, and achieves constant‑cost per cell transmission, offering significant speedups in optically thick regimes.

By Joseph A. Farmer, Aidan Murray, Johannes Krotz, Ryan G. McClarren

diffusion benchmarks

arXiv Machine Learning

Jun 5

Multi-Fidelity Learning with Shallow Recurrent Decoders for Reactor Physics

arXiv:2606. 05202v1 Announce Type: cross Abstract: In reactor physics, neutronics can be treated with different fidelity levels, according to the needs of the user.

By Stefano Riva, Carolina Introini, J. Nathan Kutz, Antonio Cammi

diffusion benchmarks

arXiv Machine Learning

Jun 16

Amortized mean-shift interacting particles

arXiv:2606. 15871v1 Announce Type: cross Abstract: Bayesian inference for inverse problems is run to evaluate integrals -- posterior expectations, tail probabilities, and risks -- across a stream of observations.

By Ali Siahkoohi

arXiv Machine Learning

Jun 5

On the training of physics-informed neural operators for solving parametric partial differential equations

arXiv:2606. 06164v1 Announce Type: new Abstract: Physics-informed neural operators (PINOs) aim to learn solution operators for partial differential equations by using the governing physics as supervision, rather than relying solely on paired input-output simulation data.

By Nanxi Chen, Chuanjie Cui, Airong Chen, Sifan Wang, Rujin Ma

llms computer-vision benchmarks

Hugging Face Trending Papers

Jun 4

On the training of physics-informed neural operators for solving parametric partial differential equations

Physics-informed neural operators (PINOs) aim to learn solution operators for partial differential equations by using the governing physics as supervision, rather than relying solely on paired input-output simulation data. By incorporating physical constraints into the training objective, PINOs combine the cross-instance generalization of neural operators with the data efficiency of physics-informed learning.

llms computer-vision benchmarks

arXiv Machine Learning

Sep 10

Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Prediction

arXiv:2609.08620v1 Announce Type: cross Abstract: We address the challenge of scalable uncertainty quantification in large-scale scientific applications, where complex state-of-the-art machine learni...

By Yousra El-Bachir, Frederik Van der Veken, Davide di Croce, Carlo Emilio Montanari, Massimo Giovannozzi, Ekaterina Krymova, Tatiana Pieloni

benchmarks

One email a morning, machine-written

Related stories

Generative Monte Carlo Sampling for Constant-Cost Particle Transport

Multi-Fidelity Learning with Shallow Recurrent Decoders for Reactor Physics

Amortized mean-shift interacting particles

On the training of physics-informed neural operators for solving parametric partial differential equations

On the training of physics-informed neural operators for solving parametric partial differential equations

Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Prediction