中文
相关论文

相关论文: Certified and accurate computation of function spa…

200 篇论文

The numerical solution of differential equations using neural networks has become a central topic in scientific computing, with Physics-Informed Neural Networks (PINNs) emerging as a powerful paradigm for both forward and inverse problems.…

机器学习 · 计算机科学 2026-01-28 Kazuaki Tanaka , Kohei Yatabe

Recent work provides promising evidence that Physics-Informed Neural Networks (PINN) can efficiently solve partial differential equations (PDE). However, previous works have failed to provide guarantees on the worst-case residual error of a…

机器学习 · 计算机科学 2024-05-30 Francisco Eiras , Adel Bibi , Rudy Bunel , Krishnamurthy Dj Dvijotham , Philip Torr , M. Pawan Kumar

We present new algorithms for a posteriori verification of neural networks (NNs) approximating solutions to PDEs. These verification algorithms compute accurate estimates of $L^p$ norms of NNs and their derivatives. When combined with…

数值分析 · 数学 2025-10-01 Emil Haugen , Alexei Stepanenko , Anders C. Hansen

We present a data-driven approach to the quantitative verification of probabilistic programs and stochastic dynamical models. Our approach leverages neural networks to compute tight and sound bounds for the probability that a stochastic…

计算机科学中的逻辑 · 计算机科学 2026-04-22 Alessandro Abate , Alec Edwards , Mirco Giacobbe , Hashan Punchihewa , Diptarko Roy

In this study, we propose a new numerical scheme for physics-informed neural networks (PINNs) that enables precise and inexpensive solution for partial differential equations (PDEs) in case of arbitrary geometries while strictly enforcing…

数值分析 · 数学 2024-07-30 Hamed Saidaoui , Luis Espath , Rául Tempone

Deep neural networks (NN) are extensively used for machine learning tasks such as image classification, perception and control of autonomous systems. Increasingly, these deep NNs are also been deployed in high-assurance applications. Thus,…

机器学习 · 计算机科学 2017-09-27 Souradeep Dutta , Susmit Jha , Sriram Sanakaranarayanan , Ashish Tiwari

Neural networks offer a computationally efficient approximation of model predictive control, but they lack guarantees on the resulting controlled system's properties. Formal certification of neural networks is crucial for ensuring safety,…

最优化与控制 · 数学 2025-02-05 Philip Sosnin , Calvin Tsay

Many core problems in nonlinear systems analysis and control can be recast as solving partial differential equations (PDEs) such as Lyapunov and Hamilton-Jacobi-Bellman (HJB) equations. Physics-informed neural networks (PINNs) have emerged…

系统与控制 · 电气工程与系统科学 2026-05-21 Jun Liu

This paper addresses the problem of formally verifying desirable properties of neural networks, i.e., obtaining provable guarantees that neural networks satisfy specifications relating their inputs and outputs (robustness to bounded norm…

机器学习 · 计算机科学 2018-08-06 Krishnamurthy , Dvijotham , Robert Stanforth , Sven Gowal , Timothy Mann , Pushmeet Kohli

We propose a very general framework for deriving rigorous bounds on the approximation error for physics-informed neural networks (PINNs) and operator learning architectures such as DeepONets and FNOs as well as for physics-informed operator…

机器学习 · 计算机科学 2022-10-11 Tim De Ryck , Siddhartha Mishra

We propose rigorous lower and upper error bounds for neural network (NN) approximations to PDEs by efficiently computing the Riesz representations of suitable extension and restrictions of the NN residual towards geometrically simpler…

数值分析 · 数学 2026-04-15 Lewin Ernst , Nikolaos Rekatsinas , Karsten Urban

Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by computing a global bound on its Lipschitz constant.…

机器学习 · 计算机科学 2021-11-03 Yujia Huang , Huan Zhang , Yuanyuan Shi , J Zico Kolter , Anima Anandkumar

With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature…

机器学习 · 计算机科学 2019-01-08 Tsui-Wei Weng , Pin-Yu Chen , Lam M. Nguyen , Mark S. Squillante , Ivan Oseledets , Luca Daniel

The traditional limitations of neural networks in reliably generalizing beyond the convex hulls of their training data present a significant problem for computational physics, in which one often wishes to solve PDEs in regimes far beyond…

机器学习 · 计算机科学 2026-02-17 Jonathan Gorard , Ammar Hakim , James Juno

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving PDEs, yet existing uncertainty quantification (UQ) approaches for PINNs generally lack rigorous statistical guarantees. In this work, we bridge this…

机器学习 · 计算机科学 2025-09-18 Yifan Yu , Cheuk Hin Ho , Yangshuai Wang

Physics-informed neural networks (PINNs) [4, 10] are an approach for solving boundary value problems based on differential equations (PDEs). The key idea of PINNs is to use a neural network to approximate the solution to the PDE and to…

数值分析 · 数学 2023-05-23 Victorita Dolean , Alexander Heinlein , Siddhartha Mishra , Ben Moseley

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs), yet they often fail to achieve accurate convergence in the H1 norm, especially in the presence of boundary…

数值分析 · 数学 2026-01-22 Qixuan Zhou , Chuqi Chen , Tao Luo , Yang Xiang

Deep neural networks exhibit remarkable performance, yet their black-box nature limits their utility in fields like healthcare where interpretability is crucial. Existing explainability approaches often sacrifice accuracy and lack…

机器学习 · 计算机科学 2025-04-08 Linhui Huang , Sayeri Lala , Niraj K. Jha

A learning method is self-certified if it uses all available data to simultaneously learn a predictor and certify its quality with a tight statistical certificate that is valid on unseen data. Recent work has shown that neural network…

Recently, deep Convolutional Neural Networks (CNNs) have proven to be successful when employed in areas such as reduced order modeling of parametrized PDEs. Despite their accuracy and efficiency, the approaches available in the literature…

数值分析 · 数学 2023-01-26 Nicola Rares Franco , Stefania Fresca , Andrea Manzoni , Paolo Zunino
‹ 上一页 1 2 3 10 下一页 ›