English
Related papers

Related papers: Operator Learning Using Weak Supervision from Walk…

200 papers

We propose Neural Walk-on-Spheres (NWoS), a novel neural PDE solver for the efficient solution of high-dimensional Poisson equations. Leveraging stochastic representations and Walk-on-Spheres methods, we develop novel losses for neural…

Machine Learning · Computer Science 2024-06-06 Hong Chul Nam , Julius Berner , Anima Anandkumar

In this paper, we investigate the Walk on Spheres algorithm (WoS) for motion planning in robotics. WoS is a Monte Carlo method to solve the Dirichlet problem developed in the 50s by Muller and has recently been repopularized by Sawhney and…

Robotics · Computer Science 2024-06-05 Rafael I. Cabral Muchacho , Florian T. Pokorny

We introduce a Monte Carlo method for computing derivatives of the solution to a partial differential equation (PDE) with respect to problem parameters (such as domain geometry or boundary conditions). Derivatives can be evaluated at…

Graphics · Computer Science 2024-09-19 Bailey Miller , Rohan Sawhney , Keenan Crane , Ioannis Gkioulekas

In this paper, we develop a highly parallel and derivative-free fractional neural walk-on-spheres method (FNWoS) for solving high-dimensional fractional Poisson equations on irregular domains. We first propose a simplified fractional…

Numerical Analysis · Mathematics 2026-02-02 Ling Guo , Mingxin Qin , Changtao Sheng , Hao Wu , Fanhai Zeng

Solving elliptic partial differential equations (PDEs) is a fundamental step in various scientific and engineering studies. As a classic stochastic solver, the Walk-on-Spheres (WoS) method is a well-established and efficient algorithm that…

Numerical Analysis · Mathematics 2025-09-03 Silei Song , Arash Fahim , Michael Mascagni

Grid-free Monte Carlo methods based on the walk on spheres (WoS) algorithm solve fundamental partial differential equations (PDEs) like the Poisson equation without discretizing the problem domain or approximating functions in a finite…

Graphics · Computer Science 2023-05-16 Rohan Sawhney , Bailey Miller , Ioannis Gkioulekas , Keenan Crane

Partial differential equations (PDEs) with spatially-varying coefficients arise throughout science and engineering, modeling rich heterogeneous material behavior. Yet conventional PDE solvers struggle with the immense complexity found in…

Graphics · Computer Science 2022-02-01 Rohan Sawhney , Dario Seyb , Wojciech Jarosz , Keenan Crane

Partial differential equation (PDE) solvers underpin scientific computing, but real-world deployment is bounded by compute. Classical Monte Carlo solvers such as Walk-on-Spheres (WoS) are unbiased and geometry-agnostic but are slow. Learned…

Machine Learning · Computer Science 2026-05-12 Ethan Hsu , Hong Meng Yam , Ivan Ge

Learning solution operators for partial differential equations (PDEs) has become a foundational task in scientific machine learning. However, existing neural operator methods require abundant training data for each specific PDE and lack the…

Machine Learning · Computer Science 2025-08-05 Yile Li , Shandian Zhe

Neural operators (NOs) provide a new paradigm for efficiently solving partial differential equations (PDEs), but their training depends on costly high-fidelity data from numerical solvers, limiting applications in complex systems. We…

Computational Physics · Physics 2026-05-18 Wen You , Shaoqian Zhou , Xuhui Meng

Recent years have witnessed the promise of coupling machine learning methods and physical domain-specific insights for solving scientific problems based on partial differential equations (PDEs). However, being data-intensive, these methods…

Machine Learning · Computer Science 2025-06-03 Wuyang Chen , Jialin Song , Pu Ren , Shashank Subramanian , Dmitriy Morozov , Michael W. Mahoney

Industrial design evaluation often relies on high-fidelity simulations of governing partial differential equations (PDEs). While accurate, these simulations are computationally expensive, making dense exploration of design spaces…

Machine Learning · Computer Science 2025-10-01 Zhizhou Zhang , Youjia Wu , Kaixuan Zhang , Yanjia Wang

Accurate modeling of spatiotemporal dynamics is crucial to understanding complex phenomena across science and engineering. However, this task faces a fundamental challenge when the governing equations are unknown and observational data are…

Computational Physics · Physics 2025-12-15 Rui Zhang , Han Wan , Yang Liu , Hao Sun

Solving partial differential equations (PDEs) is a required step in the simulation of natural and engineering systems. The associated computational costs significantly increase when exploring various scenarios, such as changes in initial or…

Learning PDE dynamics from limited data with unknown physics is challenging. Existing neural PDE solvers either require large datasets or rely on known physics (e.g., PDE residuals or handcrafted stencils), leading to limited applicability.…

Machine Learning · Computer Science 2026-05-25 Han Wan , Rui Zhang , Hao Sun

Driven by rapid advances in artificial intelligence and modern GPU computing capabilities, deep learning methods based on the optimization paradigm have provided new pathways to solve spatiotemporal physical problems, whose mathematical…

Computational Physics · Physics 2026-05-18 Shan Ding , Yongfu Tian , Lang Qin , Hongxiang Ma , Guofeng Su , Rui Yang

We propose a novel machine learning framework for solving optimization problems governed by large-scale partial differential equations (PDEs) with high-dimensional random parameters. Such optimization under uncertainty (OUU) problems may be…

Optimization and Control · Mathematics 2023-06-01 Dingcheng Luo , Thomas O'Leary-Roseberry , Peng Chen , Omar Ghattas

Optimal control problems with nonsmooth objectives and nonlinear partial differential equation (PDE) constraints are challenging, mainly because of the underlying nonsmooth and nonconvex structures and the demanding computational cost for…

Optimization and Control · Mathematics 2025-04-25 Yongcun Song , Xiaoming Yuan , Hangrui Yue , Tianyou Zeng

The Monte Carlo-type Neural Operator (MCNO) introduces a lightweight architecture for learning solution operators for parametric PDEs by directly approximating the kernel integral using a Monte Carlo approach. Unlike Fourier Neural…

Machine Learning · Computer Science 2025-11-25 Salah Eddine Choutri , Prajwal Chauhan , Othmane Mazhar , Saif Eddin Jabari

In scenarios with limited available data, training the function-to-function neural PDE solver in an unsupervised manner is essential. However, the efficiency and accuracy of existing methods are constrained by the properties of numerical…

Machine Learning · Computer Science 2025-03-12 Rui Zhang , Qi Meng , Rongchan Zhu , Yue Wang , Wenlei Shi , Shihua Zhang , Zhi-Ming Ma , Tie-Yan Liu
‹ Prev 1 2 3 10 Next ›