Gitta Kutyniok

Gitta Kutyniok

Auto-generated profile, based on publicly available information

Gitta Kutyniok

Ludwig-Maximilians-Universität München

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 June 2021 in Constructive Approximation
Verified
Journal Article
Open access
PDF file
GKGitta Kutyniok
Gitta Kutyniok
PPPhilipp Petersen
Philipp Petersen
MRMones Raslan
Mones Raslan
RSReinhold Schneider
Reinhold Schneider
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.

31 May 2019 in Inverse Problems
Verified
Journal Article
Closed access
PDF file
TBTatiana Bubba
Tatiana Bubba
GKGitta Kutyniok
Gitta Kutyniok
MLMatti Lassas
Matti Lassas
MMMaximilian Maerz
Maximilian Maerz
WSWojciech Samek
Wojciech Samek
VSVignesh Srinivasan
Vignesh Srinivasan
The high complexity of various inverse problems poses a significant challenge to model-based reconstruction schemes, which in such situations often reach their limits. At the same time, we witness an exceptional success of data-based methodologies such as deep learning. However, in the context of inverse problems, deep neural networks mostly act as black box routines, used for instance for a somewhat unspecified removal of artifacts in classical image reconstructions. In this paper, we will focus on the severely ill-posed inverse problem of limited angle computed tomography, in which entire boundary sections are not captured in the measurements. We will develop a hybrid reconstruction framework that fuses model-based sparse regularization with data-driven deep learning. Our method is reliable in the sense that we only learn the part that can provably not be handled by model-based methods, while applying the theoretically controllable sparse regularization technique to the remaining parts. Such a decomposition into visible and invisible segments is achieved by means of the shearlet transform that allows to resolve wavefront sets in the phase space. Furthermore, this split enables us to assign the clear task of inferring unknown shearlet coefficients to the neural network and thereby offering an interpretation of its performance in the context of limited angle computed tomography. Our numerical experiments show that our algorithm significantly surpasses both pure model- and more data-based reconstruction methods.

13 October 2011 in Constructive Approximation
Verified
Journal Article
Closed access
PDF file
PKPisamai Kittipoom
Pisamai Kittipoom
GKGitta Kutyniok
Gitta Kutyniok
WLWang-Q Lim
Wang-Q Lim

5 May 2021 in Constructive Approximation
Verified
Journal Article
Closed access
PDF file
RGRémi Gribonval
Rémi Gribonval
GKGitta Kutyniok
Gitta Kutyniok
MNMorten Nielsen
Morten Nielsen
FVFelix Voigtlaender
Felix Voigtlaender

6 August 2012 in Communications on Pure and Applied Mathematics
Verified
Journal Article
Closed access
PDF file
DDDavid Donoho
David Donoho
GKGitta Kutyniok
Gitta Kutyniok

5 June 2021 in Journal of Scientific Computing
Verified
Journal Article
Open access
PDF file
MGMoritz Geist
Moritz Geist
PPPhilipp Petersen
Philipp Petersen
MRMones Raslan
Mones Raslan
RSReinhold Schneider
Reinhold Schneider
GKGitta Kutyniok
Gitta Kutyniok
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.