Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
From MaRDI portal
Publication:2305540
DOI10.1007/S10444-019-09723-8zbMATH Open1435.68258arXiv1810.01348OpenAlexW3103239355MaRDI QIDQ2305540FDOQ2305540
Authors: Martin Eigel, Philipp Trunschke, S. Wolf, Reinhold Schneider 
Publication date: 11 March 2020
Published in: Advances in Computational Mathematics (Search for Journal in Brave)
Abstract: A statistical learning approach for parametric PDEs related to Uncertainty Quantification is derived. The method is based on the minimization of an empirical risk on a selected model class and it is shown to be applicable to a broad range of problems. A general unified convergence analysis is derived, which takes into account the approximation and the statistical errors. By this, a combination of theoretical results from numerical analysis and statistics is obtained. Numerical experiments illustrate the performance of the method with the model class of hierarchical tensors.
Full work available at URL: https://arxiv.org/abs/1810.01348
Recommendations
- Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
- Solving parametric PDE problems with artificial neural networks
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
- Solving Kolmogorov PDEs without the curse of dimensionality via deep learning and asymptotic expansion with Malliavin calculus
- Numerical solution of the parametric diffusion equation by deep neural networks
machine learninguncertainty quantificationstatistical learningpartial differential equationstree tensor networks
General nonlinear regression (62J02) Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05) Multilinear algebra, tensor calculus (15A69) PDEs with randomness, stochastic partial differential equations (35R60) Algorithms for approximation of functions (65D15) Numerical solution of discretized equations for boundary value problems involving PDEs (65N22) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30)
Cites Work
- An introduction to statistical learning. With applications in R
- The elements of statistical learning. Data mining, inference, and prediction
- Pattern recognition and machine learning.
- Learning Theory
- Title not available (Why is that?)
- Deep learning
- Stochastic differential equations. An introduction with applications.
- Tensor-train decomposition
- Title not available (Why is that?)
- A Stochastic Collocation Method for Elliptic Partial Differential Equations with Random Input Data
- Analytic regularity and polynomial approximation of parametric and stochastic elliptic PDE's
- Tensor spaces and numerical tensor calculus
- Online learning and online convex optimization
- An introduction to computational stochastic PDEs
- Spectral Methods for Uncertainty Quantification
- An Anisotropic Sparse Grid Stochastic Collocation Method for Partial Differential Equations with Random Input Data
- Title not available (Why is that?)
- A theory of the learnable
- On the stability and accuracy of least squares approximations
- Convergence rates of best \(N\)-term Galerkin approximations for a class of elliptic SPDEs
- Solution of stochastic partial differential equations using Galerkin finite element techniques
- Sparse tensor discretizations of high-dimensional parametric and stochastic PDEs
- Stochastic processes and applications. Diffusion processes, the Fokker-Planck and Langevin equations
- Finite Elements
- Vegas revisited: Adaptive Monte Carlo integration beyond factorization
- A new scheme for the tensor representation
- Galerkin methods for linear and nonlinear elliptic stochastic partial differential equations
- Approximation in learning theory
- Approximation of high-dimensional parametric PDEs
- Sequential sampling for optimal weighted least squares approximations in hierarchical spaces
- Numerical analysis for integral and related operator equations.
- Low rank tensor recovery via iterative hard thresholding
- Lectures on the finite element method. Notes by S. Kesavan, Akhil Ranjan, M. Vanninathan
- Decision theoretic generalizations of the PAC model for neural net and other learning applications
- Adaptive stochastic Galerkin FEM
- \(N\)-term Wiener chaos approximation rates for elliptic PDEs with lognormal Gaussian random inputs
- Theory of uniform convergence of frequencies of events to their probabilities and problems of search for an optimal solution from empirical data
- Adaptive stochastic Galerkin FEM with hierarchical tensor representations
- Tensor networks and hierarchical tensors for the solution of high-dimensional partial differential equations
- Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations
- Solving high-dimensional partial differential equations using deep learning
- Inferring solutions of differential equations using noisy multi-fidelity data
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
- Energy norm A posteriori error estimation for parametric operator equations
- An adaptive multilevel Monte Carlo method with stochastic bounds for quantities of interest with uncertain data
- Local equilibration error estimators for guaranteed error control in adaptive stochastic higher-order Galerkin finite element methods
- A convergent adaptive stochastic Galerkin finite element method with quasi-optimal spatial meshes
- Adaptive stochastic Galerkin FEM for lognormal coefficients in hierarchical tensor representations
- Machine learning of linear differential equations using Gaussian processes
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- Optimal weighted least-squares methods
- Optimal approximation with sparsely connected deep neural networks
- Solving the Kolmogorov PDE by means of deep learning
- Proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients
- Analysis of the generalization error: empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
- DeepXDE: a deep learning library for solving differential equations
- Size-independent sample complexity of neural networks
- Parametric PDEs: sparse or low-rank approximations?
- To be or not to be intrusive? The solution of parametric and stochastic equations -- proper generalized decomposition
- A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations
- Non-intrusive tensor reconstruction for high-dimensional random PDEs
- Error Estimates for Multivariate Regression on Discretized Function Spaces
Cited In (18)
- Randomized residual-based error estimators for the proper generalized decomposition approximation of parametrized problems
- Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
- Convergence of variational Monte Carlo simulation and scale-invariant pre-training
- Pricing High-Dimensional Bermudan Options with Hierarchical Tensor Formats
- Low-rank tensor reconstruction of concentrated densities with application to Bayesian inversion
- Numerical solution of the parametric diffusion equation by deep neural networks
- Title not available (Why is that?)
- A multi-level procedure for enhancing accuracy of machine learning algorithms
- Data-Driven Tensor Train Gradient Cross Approximation for Hamilton–Jacobi–Bellman Equations
- Approximative policy iteration for exit time feedback control problems driven by stochastic differential equations using tensor train format
- Probabilistic partition of unity networks for high‐dimensional regression problems
- Mini-workshop: Nonlinear approximation of high-dimensional functions in scientific computing. Abstracts from the mini-workshop held October 15--20, 2023
- Approximating the stationary Bellman equation by hierarchical tensor products
- Convergence bounds for empirical nonlinear least-squares
- Sample complexity bounds for the local convergence of least squares approximation
- Variational problems in machine learning and their solution with finite elements
- A theoretical analysis of deep neural networks and parametric PDEs
- Adaptive Nonintrusive Reconstruction of Solutions to High-Dimensional Parametric PDEs
Uses Software
This page was built for publication: Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2305540)
