Machine learning moment closure models for the radiative transfer equation III: enforcing hyperbolicity and physical characteristic speeds

• URL: http://arxiv.org/abs/2109.00700v1
• Date: Thu, 2 Sep 2021 04:16:56 GMT
• Title: Machine learning moment closure models for the radiative transfer equation III: enforcing hyperbolicity and physical characteristic speeds
• Abstract summary: Third paper in a series in which we develop machine learning (ML) moment closure models for the radiative transfer equation (RTE) Motivated by the observation that the coefficient matrix of the closure system is lower Hessenberg matrix, we relate its eigenvalues to the roots of an associated neural network.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This is the third paper in a series in which we develop machine learning (ML) moment closure models for the radiative transfer equation (RTE). In our previous work \cite{huang2021gradient}, we proposed an approach to learn the gradient of the unclosed high order moment, which performs much better than learning the moment itself and the conventional $P_N$ closure. However, while the ML moment closure has better accuracy, it is not able to guarantee hyperbolicity and has issues with long time stability. In our second paper \cite{huang2021hyperbolic}, we identified a symmetrizer which leads to conditions that enforce that the gradient based ML closure is symmetrizable hyperbolic and stable over long time. The limitation of this approach is that in practice the highest moment can only be related to four, or fewer, lower moments. In this paper, we propose a new method to enforce the hyperbolicity of the ML closure model. Motivated by the observation that the coefficient matrix of the closure system is a lower Hessenberg matrix, we relate its eigenvalues to the roots of an associated polynomial. We design two new neural network architectures based on this relation. The ML closure model resulting from the first neural network is weakly hyperbolic and guarantees the physical characteristic speeds, i.e., the eigenvalues are bounded by the speed of light. The second model is strictly hyperbolic and does not guarantee the boundedness of the eigenvalues. Several benchmark tests including the Gaussian source problem and the two-material problem show the good accuracy, stability and generalizability of our hyperbolic ML closure model.

Related papers

• A Hyperbolic Neural Closure for M1 Radiation Transfer [9.065972458046089]
  In radiation transfer simulations, an M1 method achieves substantial computational savings by replacing the full angular transport equation with a low-order moment system.<n>Because this reduced system is not closed, a closure model is required to represent the unknown higher-order moments.<n>We propose a hyperbolic neural closure for the M1 radiative transfer system to guarantee real eigenvalues.
  arXiv  Detail & Related papers  (2026-07-11T15:43:00Z)
• Machine learning moment closure models for the radiative transfer equation IV: enforcing symmetrizable hyperbolicity in two dimensions [0.0]
  This is our fourth work on machine learning (ML) moment closure models for the radiative transfer equation (RTE)<n>In the first three papers of this series, we considered the RTE in slab geometry in 1D1V.<n>We extend our framework to the RTE in 2D2V (i.e. two dimensions in physical space and two dimensions in angular space)
  arXiv  Detail & Related papers  (2026-04-22T03:12:40Z)
• Higher-order Linear Attention [59.92962330635185]
  quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts.<n>We introduce Higher-order Linear Attention (HLA), a causal, streaming mechanism that realizes higher interactions via compact prefix sufficient statistics.
  arXiv  Detail & Related papers  (2025-10-31T07:54:37Z)
• Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free [81.65559031466452]
  We conduct experiments to investigate gating-augmented softmax attention variants.<n>We find that a simple modification-applying a head-specific sigmoid gate after the Scaled Dot-Product Attention (SDPA)-consistently improves performance.
  arXiv  Detail & Related papers  (2025-05-10T17:15:49Z)
• Markovian and non-Markovian master equations versus an exactly solvable model of a qubit in a cavity [0.0]
  Quantum master equations are commonly used to model the dynamics of open quantum systems, but their accuracy is rarely compared with the analytical solution of exactly solvable models. We consider the non-Markovian time-conless master equation up to the second (Redfield) and fourth orders as well as three types of Markovian master equations. We demonstrate that the coarse-grained master equation outperforms the standard RWA-based Lindblad master equation for weak coupling or high qubit frequency.
  arXiv  Detail & Related papers  (2024-03-15T01:06:06Z)
• Determinant- and Derivative-Free Quantum Monte Carlo Within the Stochastic Representation of Wavefunctions [0.0]
  Describing the ground states of continuous, real-space quantum many-body systems is a significant computational challenge. Recent progress was made by variational methods based on machine learning (ML) ansatzes. We argue that combining SRW with path integral techniques leads to a new formulation that overcomes all three problems simultaneously.
  arXiv  Detail & Related papers  (2024-02-09T17:51:32Z)
• Tempered Calculus for ML: Application to Hyperbolic Model Embedding [70.61101116794549]
  Most mathematical distortions used in ML are fundamentally integral in nature. In this paper, we unveil a grounded theory and tools which can help improve these distortions to better cope with ML requirements. We show how to apply it to a problem that has recently gained traction in ML: hyperbolic embeddings with a "cheap" and accurate encoding along the hyperbolic vsean scale.
  arXiv  Detail & Related papers  (2024-02-06T17:21:06Z)
• Hyperbolic Machine Learning Moment Closures for the BGK Equations [0.0]
  We introduce a hyperbolic closure for the Grad moment expansion of the Bhatnagar-Gross-Krook's kinetic model using a neural network (NN) trained on BGK's moment data. This closure is motivated by the exact closure for the free streaming limit that we derived in our paper on closures in transport citeHuang2022-RTE1.
  arXiv  Detail & Related papers  (2024-01-09T19:14:57Z)
• Bridging Discrete and Backpropagation: Straight-Through and Beyond [62.46558842476455]
  We propose a novel approach to approximate the gradient of parameters involved in generating discrete latent variables. We propose ReinMax, which achieves second-order accuracy by integrating Heun's method, a second-order numerical method for solving ODEs.
  arXiv  Detail & Related papers  (2023-04-17T20:59:49Z)
• Neural Inference of Gaussian Processes for Time Series Data of Quasars [72.79083473275742]
  We introduce a new model that enables it to describe quasar spectra completely. We also introduce a new method of inference of Gaussian process parameters, which we call $textitNeural Inference$. The combination of both the CDRW model and Neural Inference significantly outperforms the baseline DRW and MLE.
  arXiv  Detail & Related papers  (2022-11-17T13:01:26Z)
• Off-the-grid learning of mixtures from a continuous dictionary [2.774897240515734]
  We consider a general non-linear model where the signal is a finite mixture of unknown, possibly increasing, number of features issued from a continuous dictionary parameterized by a real non-linear parameter. We propose an off-the-grid optimization method, that is, a method which does not use any discretization scheme on the parameter space. We establish convergence rates that quantify with high probability the quality of estimation for both the linear and the non-linear parameters.
  arXiv  Detail & Related papers  (2022-06-29T07:55:20Z)
• Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization [50.83356836818667]
  gradient Langevin Dynamics is one of the most fundamental algorithms to solve non-eps optimization problems. In this paper, we show two variants of this kind, namely the Variance Reduced Langevin Dynamics and the Recursive Gradient Langevin Dynamics.
  arXiv  Detail & Related papers  (2022-03-30T11:39:00Z)
• Machine learning moment closure models for the radiative transfer equation II: enforcing global hyperbolicity in gradient based closures [0.0]
  This is the second paper in a series in which we develop machine learning (ML) moment closure models for the radiative transfer equation (RTE) We propose a method to enforce the global hyperbolicity of the ML closure model. It is shown that the new ML closure system inherits the dissipativeness of the RTE and preserves the correct diffusion limit as the Knunsden number goes to zero.
  arXiv  Detail & Related papers  (2021-05-30T02:10:59Z)
• Machine learning moment closure models for the radiative transfer equation I: directly learning a gradient based closure [0.0]
  We propose to learn the gradient of the high order moment using neural networks. A variety of benchmark tests, including the variable scattering problem, show both good accuracy and generalizability of our machine learning closure model.
  arXiv  Detail & Related papers  (2021-05-12T14:24:20Z)
• Online nonparametric regression with Sobolev kernels [99.12817345416846]
  We derive the regret upper bounds on the classes of Sobolev spaces $W_pbeta(mathcalX)$, $pgeq 2, beta>fracdp$. The upper bounds are supported by the minimax regret analysis, which reveals that in the cases $beta> fracd2$ or $p=infty$ these rates are (essentially) optimal.
  arXiv  Detail & Related papers  (2021-02-06T15:05:14Z)
• Gaussian MRF Covariance Modeling for Efficient Black-Box Adversarial Attacks [86.88061841975482]
  We study the problem of generating adversarial examples in a black-box setting, where we only have access to a zeroth order oracle. We use this setting to find fast one-step adversarial attacks, akin to a black-box version of the Fast Gradient Sign Method(FGSM) We show that the method uses fewer queries and achieves higher attack success rates than the current state of the art.
  arXiv  Detail & Related papers  (2020-10-08T18:36:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.