面向机器学习与不确定性量化中随机算子模型的紧致无边界多连通流形上的物理信息随机神经架构
Physics-informed random neural architectures on compact boundaryless multiply connected manifolds for random-operator models in machine learning and uncertainty quantification
AI总结:
该研究提出SPINNs,通过公共高斯随机种子耦合SBVP随机算子与流形随机神经架构,在观测空间训练,避免PDE残差损失,经随机椭圆问题验证,可用于SBVP相关建模与超参数推断。
摘要:
我们提出了适用于含随机算子的随机边值问题(SBVPs)的随机物理信息神经网络(SPINNs)。该方法通过结构概率耦合来嵌入物理规律:一个公共高斯随机“种子”同时驱动SBVP随机算子和基于流形的随机神经架构。该随机神经网络(SNN)为非前馈型且具有内在随机性,紧致无边界多连通流形上的潜在高斯场与非齐次泊松点过程共同生成随机神经元位置、测地线局部稀疏连接及稀疏随机权重矩阵,所有这些均由低维超参数控制。对于确定性输入,网络输出为随机量,可表示非高斯随机算子。训练在观测空间中进行:SBVP模拟产生随机可观测量,而SNN定义预测条件概率密度函数。监督目标函数结合了通过负对数似然实现的数据保真项,以及相对于SBVP诱导条件分布的交叉熵对齐项。所得目标为观测诱导分布与SBVP诱导分布的凸混合,其中无量纲参数控制对模型-数据不匹配的鲁棒性。公共随机种子可产生公共随机数蒙特卡洛估计量并降低梯度方差。该方法仅使用SBVP解映射的评估,无需对其求导或修改,且避免了PDE残差或边界惩罚损失。周期圆柱面上的随机椭圆问题在SBVP一致与SBVP误设定两种场景下验证了该方法,同时还概述了用于超参数推断和后验平均的广义后验公式,无需针对每个查询重新优化。
英文摘要:
We introduce stochastic physics-informed neural networks (SPINNs) for stochastic boundary-value problems (SBVPs) with random operators. The method enforces physics through a structural probabilistic coupling: a common Gaussian stochastic germ drives both the SBVP random operator and a manifold-based stochastic neural architecture. The stochastic neural network is non-feedforward and intrinsically random. A latent Gaussian field and an inhomogeneous Poisson point process on a compact, boundaryless, multiply connected manifold generate random neuron locations, geodesically local sparse connectivity, and a sparse random weight matrix, all governed by a low-dimensional hyperparameter. For deterministic inputs, the network output is random and can represent non-Gaussian random operators. Training is performed in observation space: SBVP simulations produce random observables, while the SNN defines a predictive conditional probability density function. The supervised objective combines data fidelity, through negative log-likelihood, with a cross-entropy alignment term relative to the SBVP-induced conditional distribution. The resulting target is a convex mixture of observation-induced and SBVP-induced distributions, with a dimensionless parameter controlling robustness to model--data mismatch. The shared stochastic germ yields common-random-numbers Monte Carlo estimators and reduced-variance gradients. The method uses only evaluations of the SBVP solution mapping, without differentiating or modifying it, and avoids PDE-residual or boundary-penalty losses. A stochastic elliptic problem on a periodic cylindrical surface illustrates the approach in SBVP-consistent and SBVP-misspecified regimes. A generalized-posterior formulation is also outlined for hyperparameter inference and posterior averaging without per-query reoptimization.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。