Reinhold Schneider
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Reinhold Schneider has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Gitta Kutyniok
Ludwig-Maximilians-Universität München
4 shared publications - Martin Eigel
Weierstrass Institute, Berlin, Germany
4 shared publications - Mones Raslan
Institut für Mathematik, Technische Universität Berlin, Berlin, Germany
4 shared publications - Philipp Petersen
Faculty of Mathematics and Research Network Data Science Uni Vienna University of Vienna Austria
4 shared publications - Thorsten Rohwedder
Sekretariat MA 5-3, Institut für Mathematik, TU Berlin, Straße des 17. Juni 136, 10623 Berlin, Germany
4 shared publications - Wolfgang Dahmen
Institut für Geometrie und Praktische Mathematik RWTH Aachen Templergraben 55 52056 Aachen Germany
4 shared publications
Latest Publications
- 4 December 2024
- Published by Springer Nature
- p. 383-403
Towards Continuous Mathematical Models for the Analysis of Classes of Deep Neural Networks
- 4 December 2024
- Published by Springer Nature
- p. 383-403
Towards Continuous Mathematical Models for the Analysis of Classes of Deep Neural Networks
- 7 March 2023
- Published by American Mathematical Society (AMS) in Mathematics of Computation
- Vol. 92 (342) , 1729-1746
Low-rank approximation of continuous functions in Sobolev spaces with dominating mixed smoothness
Let Ω i ⊂ R n i \Omega _i\subset \mathbb {R}^{n_i} , i = 1 , … , m i=1,\ldots ,m , be given domains. In this article, we study the low-rank approximation with respect to L 2 ( Ω 1 × ⋯ × Ω m ) L^2(\Omega _1\times \dots \times \Omega _m) of functions from Sobolev spaces with dominating mixed smoothness. To this end, we first estimate the rank of a bivariate approximation, i.e., the rank of the continuous singular value decomposition. In comparison to the case of functions from Sobolev spaces with isotropic smoothness, compare Griebel and Harbrecht [IMA J. Numer. Anal. 34 (2014), pp. 28–54] and Griebel and Harbrecht [IMA J. Numer. Anal. 39 (2019), pp. 1652–1671], we obtain improved results due to the additional mixed smoothness. This convergence result is then used to study the tensor train decomposition as a method to construct multivariate low-rank approximations of functions from Sobolev spaces with dominating mixed smoothness. We show that this approach is able to beat the curse of dimension.
- 7 March 2023
- Published by American Mathematical Society (AMS) in Mathematics of Computation
- Vol. 92 (342) , 1729-1746
Low-rank approximation of continuous functions in Sobolev spaces with dominating mixed smoothness
Let Ω i ⊂ R n i \Omega _i\subset \mathbb {R}^{n_i} , i = 1 , … , m i=1,\ldots ,m , be given domains. In this article, we study the low-rank approximation with respect to L 2 ( Ω 1 × ⋯ × Ω m ) L^2(\Omega _1\times \dots \times \Omega _m) of functions from Sobolev spaces with dominating mixed smoothness. To this end, we first estimate the rank of a bivariate approximation, i.e., the rank of the continuous singular value decomposition. In comparison to the case of functions from Sobolev spaces with isotropic smoothness, compare Griebel and Harbrecht [IMA J. Numer. Anal. 34 (2014), pp. 28–54] and Griebel and Harbrecht [IMA J. Numer. Anal. 39 (2019), pp. 1652–1671], we obtain improved results due to the additional mixed smoothness. This convergence result is then used to study the tensor train decomposition as a method to construct multivariate low-rank approximations of functions from Sobolev spaces with dominating mixed smoothness. We show that this approach is able to beat the curse of dimension.
- 19 December 2022
- Published by Springer Nature
- p. 427-445
Augmented Plane Wave Methods for Full-Potential Calculations
- 19 December 2022
- Published by Springer Nature
- p. 427-445
Augmented Plane Wave Methods for Full-Potential Calculations
- Open Access
Low-rank approximation of continuous functions in Sobolev spaces with dominating mixed smoothness
Let $\Omega_i\subset\mathbb{R}^{n_i}$, $i=1,\ldots,m$, be given domains. In this article, we study the low-rank approximation with respect to $L^2(\Omega_1\times\dots\times\Omega_m)$ of functions from Sobolev spaces with dominating mixed smoothness. To this end, we first estimate the rank of a bivariate approximation, i.e., the rank of the continuous singular value decomposition. In comparison to the case of functions from Sobolev spaces with isotropic smoothness, compare \cite{GH14,GH19}, we obtain improved results due to the additional mixed smoothness. This convergence result is then used to study the tensor train decomposition as a method to construct multivariate low-rank approximations of functions from Sobolev spaces with dominating mixed smoothness. We show that this approach is able to beat the curse of dimension.Open AccessLow-rank approximation of continuous functions in Sobolev spaces with dominating mixed smoothness
Let $\Omega_i\subset\mathbb{R}^{n_i}$, $i=1,\ldots,m$, be given domains. In this article, we study the low-rank approximation with respect to $L^2(\Omega_1\times\dots\times\Omega_m)$ of functions from Sobolev spaces with dominating mixed smoothness. To this end, we first estimate the rank of a bivariate approximation, i.e., the rank of the continuous singular value decomposition. In comparison to the case of functions from Sobolev spaces with isotropic smoothness, compare \cite{GH14,GH19}, we obtain improved results due to the additional mixed smoothness. This convergence result is then used to study the tensor train decomposition as a method to construct multivariate low-rank approximations of functions from Sobolev spaces with dominating mixed smoothness. We show that this approach is able to beat the curse of dimension. - 21 June 2022
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 44 (3) , B746-B770
Approximating Optimal feedback Controllers of Finite Horizon Control Problems Using Hierarchical Tensor Formats
Controlling systems of ordinary differential equations is ubiquitous in science and engineering. For finding an optimal feedback controller, the value function and associated fundamental equations ...
- 21 June 2022
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 44 (3) , B746-B770
Approximating Optimal feedback Controllers of Finite Horizon Control Problems Using Hierarchical Tensor Formats
Controlling systems of ordinary differential equations is ubiquitous in science and engineering. For finding an optimal feedback controller, the value function and associated fundamental equations ...
- 21 March 2022
- Published by Society for Industrial & Applied Mathematics (SIAM) in Multiscale Modeling & Simulation
- Vol. 20 (1) , 379-403
Approximative Policy Iteration for Exit Time Feedback Control Problems Driven by Stochastic Differential Equations using Tensor Train Format
We consider a stochastic optimal exit time feedback control problem. The Bellman equation is solved approximatively via the Policy Iteration algorithm on a polynomial ansatz space by a sequence of ...
- 21 March 2022
- Published by Society for Industrial & Applied Mathematics (SIAM) in Multiscale Modeling & Simulation
- Vol. 20 (1) , 379-403
Approximative Policy Iteration for Exit Time Feedback Control Problems Driven by Stochastic Differential Equations using Tensor Train Format
We consider a stochastic optimal exit time feedback control problem. The Bellman equation is solved approximatively via the Policy Iteration algorithm on a polynomial ansatz space by a sequence of ...
- Open Access
Approximation by tree tensor networks in high dimensions: Sobolev and compositional functions
This paper is concerned with convergence estimates for fully discrete tree tensor network approximations of high-dimensional functions from several model classes. For functions having standard or mixed Sobolev regularity, new estimates generalizing and refining known results are obtained, based on notions of linear widths of multivariate functions. In the main results of this paper, such techniques are applied to classes of functions with compositional structure, which are known to be particularly suitable for approximation by deep neural networks. As shown here, such functions can also be approximated by tree tensor networks without a curse of dimensionality -- however, subject to certain conditions, in particular on the depth of the underlying tree. In addition, a constructive encoding of compositional functions in tree tensor networks is given.
Open AccessApproximation by tree tensor networks in high dimensions: Sobolev and compositional functions
This paper is concerned with convergence estimates for fully discrete tree tensor network approximations of high-dimensional functions from several model classes. For functions having standard or mixed Sobolev regularity, new estimates generalizing and refining known results are obtained, based on notions of linear widths of multivariate functions. In the main results of this paper, such techniques are applied to classes of functions with compositional structure, which are known to be particularly suitable for approximation by deep neural networks. As shown here, such functions can also be approximated by tree tensor networks without a curse of dimensionality -- however, subject to certain conditions, in particular on the depth of the underlying tree. In addition, a constructive encoding of compositional functions in tree tensor networks is given.
- Top Cited PapersOpen Access
- 5 June 2021
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 88 (1) , 1-37
Numerical Solution of the Parametric Diffusion Equation by Deep Neural Networks
We perform a comprehensive numerical study of the effect of approximation-theoretical results for neural networks on practical learning problems in the context of numerical analysis. As the underlying model, we study the machine-learning-based solution of parametric partial differential equations. Here, approximation theory for fully-connected neural networks predicts that the performance of the model should depend only very mildly on the dimension of the parameter space and is determined by the intrinsic dimension of the solution manifold of the parametric partial differential equation. We use various methods to establish comparability between test-cases by minimizing the effect of the choice of test-cases on the optimization and sampling aspects of the learning problem. We find strong support for the hypothesis that approximation-theoretical effects heavily influence the practical behavior of learning problems in numerical analysis. Turning to practically more successful and modern architectures, at the end of this study we derive improved error bounds by focusing on convolutional neural networks.
- 5 June 2021
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 88 (1) , 1-37
Top Cited PapersOpen AccessNumerical Solution of the Parametric Diffusion Equation by Deep Neural Networks
We perform a comprehensive numerical study of the effect of approximation-theoretical results for neural networks on practical learning problems in the context of numerical analysis. As the underlying model, we study the machine-learning-based solution of parametric partial differential equations. Here, approximation theory for fully-connected neural networks predicts that the performance of the model should depend only very mildly on the dimension of the parameter space and is determined by the intrinsic dimension of the solution manifold of the parametric partial differential equation. We use various methods to establish comparability between test-cases by minimizing the effect of the choice of test-cases on the optimization and sampling aspects of the learning problem. We find strong support for the hypothesis that approximation-theoretical effects heavily influence the practical behavior of learning problems in numerical analysis. Turning to practically more successful and modern architectures, at the end of this study we derive improved error bounds by focusing on convolutional neural networks.
- Top Cited PapersOpen Access
- 2 June 2021
- Published by Springer Nature in Constructive Approximation
- Vol. 55 (1) , 73-125
A Theoretical Analysis of Deep Neural Networks and Parametric PDEs
We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent low dimensionality of the solution manifold to obtain approximation rates which are significantly superior to those provided by classical neural network approximation results. Concretely, we use the existence of a small reduced basis to construct, for a large variety of parametric partial differential equations, neural networks that yield approximations of the parametric solution maps in such a way that the sizes of these networks essentially only depend on the size of the reduced basis.
- 2 June 2021
- Published by Springer Nature in Constructive Approximation
- Vol. 55 (1) , 73-125
Top Cited PapersOpen AccessA Theoretical Analysis of Deep Neural Networks and Parametric PDEs
We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent low dimensionality of the solution manifold to obtain approximation rates which are significantly superior to those provided by classical neural network approximation results. Concretely, we use the existence of a small reduced basis to construct, for a large variety of parametric partial differential equations, neural networks that yield approximations of the parametric solution maps in such a way that the sizes of these networks essentially only depend on the size of the reduced basis.