发表机构
The University of Tokyo; National Institute for Fusion Science（东京大学; 国立核聚变科学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对聚变等离子体诊断中MCMC贝叶斯推理的计算瓶颈与噪声敏感性问题，提出双头架构的异方差神经代理框架，实现超1500倍加速且降低20%以上推理误差，为实时物理分析提供新范式。
AI 中文摘要
马尔可夫链蒙特卡洛（MCMC）方法实现的贝叶斯推理可提供有效的参数估计，但其在复杂物理系统中的实时应用受限于沉重的计算瓶颈和对统计噪声的极端敏感性。针对该问题，本文提出一种基于神经网络的概率代理框架，用于快速且鲁棒的MCMC推理。以噪声占主导的聚变等离子体汤姆逊散射诊断作为具有挑战性的测试平台，所提方法采用双头架构，同时估计预期的物理发射光谱和通道内固有的测量噪声方差。通过优化高斯负对数似然（GNLL）目标函数，学习到的偶然不确定性可动态缓冲采样器以抵御病态散粒噪声。评估结果表明，该代理框架相较于精确物理正向模型实现了超过1500倍的加速，同时相较于标准同方差神经基线将推理误差（RMSE）降低了20%以上，为实时物理分析提供了极具前景的范式。
英文摘要
Bayesian inference via Markov Chain Monte Carlo (MCMC) provides effective parameter estimation, but its real-time application in complex physical systems is hindered by heavy computational bottlenecks and extreme sensitivity to statistical noise. We address this by proposing a neural-network-based probabilistic surrogate framework for rapid and robust MCMC inference. Using fusion plasma Thomson scattering diagnostics as a challenging, noise-dominated testbed, our approach employs a dual-head architecture to simultaneously estimate the expected physical emission spectrum and the channel-wise intrinsic measurement noise variance. By optimizing a Gaussian Negative Log-Likelihood (GNLL) objective, the learned aleatoric uncertainty dynamically buffers the sampler against pathological shot noise. Evaluations demonstrate that this surrogate framework achieves > 1500x acceleration over exact physical forward models, while simultaneously reducing inference error (RMSE) by >20% compared to standard homoscedastic neural baselines, offering a highly promising paradigm for real-time physical analysis.
Comments8 pages, 3 figures
