English
Related papers

Related papers: Robin Pre-Training for the Deep Ritz Method

200 papers

We establish error estimates for the approximation of parametric $p$-Dirichlet problems deploying the Deep Ritz Method. Parametric dependencies include, e.g., varying geometries and exponents $p\in (1,\infty)$. Combining the derived error…

Numerical Analysis · Mathematics 2022-07-06 Alex Kaltenbach , Marius Zeinhofer

Using a capacity approach, and the theory of measure's perturbation of Dirichlet forms, we give the probabilistic representation of the General Robin boundary value problems on an arbitrary domain $\Omega$, involving smooth measures, which…

Probability · Mathematics 2013-03-26 Khalid Akhlil

We present a new view onto the successive approximations' approach in study of the two-point nonlinear fractional boundary value problems. In order to reduce the original problem and further construct its approximate solution we use the…

Classical Analysis and ODEs · Mathematics 2021-01-22 Kateryna Marynets

Reinforcement learning (RL) is attracting attention as an effective way to solve sequential optimization problems that involve high dimensional state/action space and stochastic uncertainties. Many such problems involve constraints…

Machine Learning · Computer Science 2021-04-01 Haeun Yoo , Victor M. Zavala , Jay H. Lee

We consider the torsional rigidity and the principal eigenvalue related to the Laplace operator with Dirichlet and Robin boundary conditions. The goal is to find upper and lower bounds to products of suitable powers of the quantities above…

Analysis of PDEs · Mathematics 2025-12-18 Giuseppe Buttazzo , Simone Cito , Francesco Solombrino

While much attention of neural network methods is devoted to high-dimensional PDE problems, in this work we consider methods designed to work for elliptic problems on domains $\Omega \subset \mathbb{R} ^d, $ $d=1,2,3$ in association with…

Numerical Analysis · Mathematics 2025-02-06 Georgios Grekas , Charalambos G. Makridakis

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Machine Learning · Computer Science 2021-10-28 Mete Kemertas , Tristan Aumentado-Armstrong

We introduce a new constructive method for establishing lower bounds on convergence rates of periodic homogenization problems associated with divergence type elliptic operators. The construction is applied in two settings. First, we show…

Analysis of PDEs · Mathematics 2016-12-28 Hayk Aleksanyan

Linear second order elliptic boundary value problems (BVP) on bounded Lipschitz domains are studied in the case of Gaussian white noise loads. Especially, Neumann and Robin BVPs are considered. The main obstacle for applying the usual…

Probability · Mathematics 2016-03-03 Sari Lasanen , Lassi Roininen , Janne M. J. Huttunen

In this paper, we study the Dirichlet boundary value problem of steady-state relativistic Boltzmann equation in half-line with hard potential model, given the data for the outgoing particles at the boundary and a relativistic global…

Analysis of PDEs · Mathematics 2024-11-12 Yi Wang , Li Li , Zaihong Jiang

This paper concerns the a priori generalization analysis of the Deep Ritz Method (DRM) [W. E and B. Yu, 2017], a popular neural-network-based method for solving high dimensional partial differential equations. We derive the generalization…

Numerical Analysis · Mathematics 2021-03-23 Jianfeng Lu , Yulong Lu , Min Wang

Typical reinforcement learning (RL) methods show limited applicability for real-world industrial control problems because industrial systems involve various constraints and simultaneously require continuous and discrete control. To overcome…

Artificial Intelligence · Computer Science 2021-05-20 Hyungjun Park , Daiki Min , Jong-hyun Ryu , Dong Gu Choi

Many state-of-the-art adversarial training methods for deep learning leverage upper bounds of the adversarial loss to provide security guarantees against adversarial attacks. Yet, these methods rely on convex relaxations to propagate lower…

Machine Learning · Computer Science 2023-04-07 Dimitris Bertsimas , Xavier Boix , Kimberly Villalobos Carballo , Dick den Hertog

In this paper, we present a new iterative approximate method of solving boundary value problems. The idea is to compute approximate polynomial solutions in the Bernstein form using least squares approximation combined with some properties…

Numerical Analysis · Computer Science 2017-09-08 Przemysław Gospodarczyk , Paweł Woźny

The solution to partial differential equations using deep learning approaches has shown promising results for several classes of initial and boundary-value problems. However, their ability to surpass, particularly in terms of accuracy,…

Numerical Analysis · Mathematics 2023-08-23 Ziad Aldirany , Régis Cottereau , Marc Laforest , Serge Prudhomme

A Neural Network (NN) based numerical method is formulated and implemented for solving Boundary Value Problems (BVPs) and numerical results are presented to validate this method by solving Laplace equation with Dirichlet boundary condition…

Machine Learning · Computer Science 2019-09-25 Sethu Hareesh Kolluru

This work proposes a nonlinear finite element method whose nodal values preserve bounds known for the exact solution. The discrete problem involves a nonlinear projection operator mapping arbitrary nodal values into bound-preserving ones…

Numerical Analysis · Mathematics 2023-04-04 Gabriel Barrenechea , Emmanuil Georgoulis , Tristan Pryer , Andreas Veeser

In this paper, we prove that there exists a unique, bounded continuous weak solution to the Dirichlet boundary value problem for a general class of second-order elliptic operators with singular coefficients, which does not necessarily have…

Probability · Mathematics 2009-07-27 Zhen-Qing Chen , Tusheng Zhang

In this article we establish an approximation result involving the Laplacian with Robin boundary conditions. It informs about the weak solutions dependence from the input function on the boundary.

Analysis of PDEs · Mathematics 2014-05-20 Khalid Akhlil

Strong worst-case performance bounds for episodic reinforcement learning exist but fortunately in practice RL algorithms perform much better than such bounds would predict. Algorithms and theory that provide strong problem-dependent bounds…

Machine Learning · Computer Science 2019-11-05 Andrea Zanette , Emma Brunskill