paper-with-me

Papers

Learning Stochastic Dynamics with Statistics-Informed Neural Network

2022-02-24 · Yuanran Zhu, Yu-Hang Tang, Changho Kim

We introduce a machine-learning framework named statistics-informed neural network (SINN) for learning stochastic dynamics from data. This new architecture was theoretically inspired by a universal approximation theorem for stochastic systems, which we introduce in this paper, and the projection-operator formalism for stochastic modeling. We devise mechanisms for training the neural network model to reproduce the correct \emph{statistical} behavior of a target stochastic process. Numerical simulation results demonstrate that a well-trained SINN can reliably approximate both Markovian and non-Markovian stochastic dynamics. We demonstrate the applicability of SINN to coarse-graining problems and the modeling of transition dynamics. Furthermore, we show that the obtained reduced-order model can be trained on temporally coarse-grained data and hence is well suited for rare-event simulations.

📄 PDF Abstract BibTeX arXiv:2202.12278

Code (1)

sinn-model/sinn 공식 구현 pytorch

Similar Papers 제목 키워드 기반

VISP: Volatility Informed Stochastic Projection for Adaptive Regularization

2025-09-02 · Tanvir Islam arxiv

We propose VISP: Volatility Informed Stochastic Projection, an adaptive regularization method that leverages gradient volatility to guide stochastic noise injection in deep neural networks. Unlike conventional techniques…

Physics-Informed Gaussian Process Regression for Probabilistic States Estimation and Forecasting in Power Grids

2020-10-09 · Tong Ma, David Alonso Barajas-Solano, Ramakrishna Tipireddy, Alexandre M. Tartakovsky

Real-time state estimation and forecasting is critical for efficient operation of power grids. In this paper, a physics-informed Gaussian process regression (PhI-GPR) method is presented and used for probabilistic foreca…

GPRregressionState Estimation

Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent

2023-02-14 · Benjamin Gess, Sebastian Kassing, Vitalii Konarovskyi

We propose new limiting dynamics for stochastic gradient descent in the small learning rate regime called stochastic modified flows. These SDEs are driven by a cylindrical Brownian motion and improve the so-called stocha…

Differentiable Stochastic Traffic Dynamics: Physics-Informed Generative Modelling in Transportation

2026-03-10 · Wuping Xin arxiv

Macroscopic traffic flow is stochastic, but the physics-informed deep learning methods currently used in transportation literature embed deterministic PDEs and produce point-valued outputs; the stochasticity of the gover…

When Bifidelity Meets CoKriging: An Efficient Physics-Informed Multifidelity Method

2018-12-07 · Xiu Yang, Xueyu Zhu, Jing Li

In this work, we propose a framework that combines the approximation-theory-based multifidelity method and Gaussian-process-regression-based multifidelity method to achieve data-model convergence when stochastic simulati…