Gabriele Steidl
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Gabriele Steidl has a total of 144 co-authors. Here are the top co-authors by number of shared publications:
- Sebastian Neumayer
Chemnitz University of Technology, Chemnitz, Germany
11 shared publications - Johannes Hertrich
Institute of Mathematics Technische Universität Berlin Strasse des 17. Juni 136 D-10623 Berlin Germany
10 shared publications - Jan Henrik Fitschen
Department of Mathematics, University of Kaiserslautern, Kaiserslautern, Germany
9 shared publications - Gerd Teschke
Institute for Computational Mathematics in Science and Technology, University of Applied Sciences Neubrandenburg, Brodaer Str. 2, 17033 Neubrandenburg, Germany
8 shared publications - Robert Beinert
Institut für Mathematik, Technische Universität Berlin, Berlin, Germany
8 shared publications - Michael Quellmalz
Institute of Mathematics, Technische Universität Berlin, Berlin, Germany
7 shared publications
Latest Publications
- 25 October 2026
- Published by Springer Nature in Constructive Approximation
- p. 1-49
Unsupervised Ground Metric Learning
- 25 October 2026
- Published by Springer Nature in Constructive Approximation
- p. 1-49
Unsupervised Ground Metric Learning
- 5 August 2026
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 68 (4) , 53
HOT-POT: Optimal Transport for Sparse Stereo Matching
- 5 August 2026
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 68 (4) , 53
HOT-POT: Optimal Transport for Sparse Stereo Matching
- Open Access
- 21 July 2026
- Published by European Mathematical Society - EMS - Publishing House GmbH in Oberwolfach Reports
- Vol. 23 (1) , 795-884
Flows on Measure Spaces and Applications in Machine Learning
Flows on measure spaces have long been examined in stochastic analysis and have recently attracted significant interest in machine learning, leading to intriguing research questions that often fall outside the scope of existing theory. Normalizing flows, score-based diffusion, and flow matching models are among the most powerful generative neural methods and rely on the geometry of measure spaces. In particular, the Wasserstein metric and optimal transport techniques have advanced the field in recent years. However, involving different Riemannian-like metrics on measure spaces, e.g., by the framework of right-invariant metrics on the group of diffeomorphisms and their action on objects, e.g., densities, and designing transport inference functionals with advanced properties like equivariance led to new neural models. Generative models can be conditioned on (degraded) data, which leads to new developments in the solution of Bayesian inverse problems. Viewing transformers as interacting particle systems introduced a new mathematical perspective on these complex systems and shed light on their clustering behavior. Finally, learning neural models comes with new challenges in (stochastic) optimization, such as accelerated optimization, operator splitting, and mirror descent on measure spaces, ensemble filtering methods, the treatment of high dimensions via slicing or Fourier random features, as well as scalability questions and related lifting to infinite-dimensional spaces. The workshop will bring together scientists interested in different aspects of flows on measure spaces to further understand and develop their analysis, in particular to address questions in deep generative learning and to develop improved optimization methods for measure spaces.
- 21 July 2026
- Published by European Mathematical Society - EMS - Publishing House GmbH in Oberwolfach Reports
- Vol. 23 (1) , 795-884
Open AccessFlows on Measure Spaces and Applications in Machine Learning
Flows on measure spaces have long been examined in stochastic analysis and have recently attracted significant interest in machine learning, leading to intriguing research questions that often fall outside the scope of existing theory. Normalizing flows, score-based diffusion, and flow matching models are among the most powerful generative neural methods and rely on the geometry of measure spaces. In particular, the Wasserstein metric and optimal transport techniques have advanced the field in recent years. However, involving different Riemannian-like metrics on measure spaces, e.g., by the framework of right-invariant metrics on the group of diffeomorphisms and their action on objects, e.g., densities, and designing transport inference functionals with advanced properties like equivariance led to new neural models. Generative models can be conditioned on (degraded) data, which leads to new developments in the solution of Bayesian inverse problems. Viewing transformers as interacting particle systems introduced a new mathematical perspective on these complex systems and shed light on their clustering behavior. Finally, learning neural models comes with new challenges in (stochastic) optimization, such as accelerated optimization, operator splitting, and mirror descent on measure spaces, ensemble filtering methods, the treatment of high dimensions via slicing or Fourier random features, as well as scalability questions and related lifting to infinite-dimensional spaces. The workshop will bring together scientists interested in different aspects of flows on measure spaces to further understand and develop their analysis, in particular to address questions in deep generative learning and to develop improved optimization methods for measure spaces.
- Open Access
- 10 June 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (6) , 315
Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs
We propose two graph neural network layers for graphs with features in a Riemannian manifold. First, based on a manifold-valued graph diffusion equation, we construct a diffusion layer that can be applied to an arbitrary number of nodes and graph connectivity patterns. Second, we model a tangent multilayer perceptron by transferring ideas from the vector neuron framework to our general setting. Both layers are equivariant under node permutations and the feature manifold’s isometries. These properties have led to a beneficial inductive bias in many deep-learning tasks. Furthermore, they enable novel, more flexible feature designs. Numerical examples on synthetic data and an Alzheimer’s classification application on triangle meshes of the right hippocampus demonstrate the usefulness of our new layers: While they apply to a much broader class of problems, they outperform task-specific state-of-the-art networks.
- 10 June 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (6) , 315
Open AccessManifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs
We propose two graph neural network layers for graphs with features in a Riemannian manifold. First, based on a manifold-valued graph diffusion equation, we construct a diffusion layer that can be applied to an arbitrary number of nodes and graph connectivity patterns. Second, we model a tangent multilayer perceptron by transferring ideas from the vector neuron framework to our general setting. Both layers are equivariant under node permutations and the feature manifold’s isometries. These properties have led to a beneficial inductive bias in many deep-learning tasks. Furthermore, they enable novel, more flexible feature designs. Numerical examples on synthetic data and an Alzheimer’s classification application on triangle meshes of the right hippocampus demonstrate the usefulness of our new layers: While they apply to a much broader class of problems, they outperform task-specific state-of-the-art networks.
- Open Access
- 27 March 2026
- Published by Springer Nature in Advances in Computational Mathematics
- Vol. 52 (2) , 24
Smoothed distance kernels for MMDs and applications in Wasserstein gradient flows
Negative distance kernels $$K(x,y) := - \Vert x-y\Vert $$ were used in the definition of maximum mean discrepancies (MMDs) in statistics and lead to favorable numerical results in various applications. In particular, so-called slicing techniques for handling high-dimensional kernel summations profit from the simple parameter-free structure of the distance kernel. However, due to its non-smoothness in $$x=y$$ , most of the classical theoretical results, e.g., on Wasserstein gradient flows of the corresponding MMD functional, no longer hold true. In this paper, we propose a new kernel which keeps the favorable properties of the negative distance kernel as being conditionally positive definite of order one with a nearly linear increase towards infinity and a simple slicing structure, but is Lipschitz differentiable now. Our construction is based on a simple 1D smoothing procedure of the absolute value function followed by a Riemann–Liouville fractional integral transform. Numerical results demonstrate that the new kernel performs similarly well as the negative distance kernel in gradient descent methods, but now with theoretical guarantees.- 27 March 2026
- Published by Springer Nature in Advances in Computational Mathematics
- Vol. 52 (2) , 24
Open AccessSmoothed distance kernels for MMDs and applications in Wasserstein gradient flows
Negative distance kernels $$K(x,y) := - \Vert x-y\Vert $$ were used in the definition of maximum mean discrepancies (MMDs) in statistics and lead to favorable numerical results in various applications. In particular, so-called slicing techniques for handling high-dimensional kernel summations profit from the simple parameter-free structure of the distance kernel. However, due to its non-smoothness in $$x=y$$ , most of the classical theoretical results, e.g., on Wasserstein gradient flows of the corresponding MMD functional, no longer hold true. In this paper, we propose a new kernel which keeps the favorable properties of the negative distance kernel as being conditionally positive definite of order one with a nearly linear increase towards infinity and a simple slicing structure, but is Lipschitz differentiable now. Our construction is based on a simple 1D smoothing procedure of the absolute value function followed by a Riemann–Liouville fractional integral transform. Numerical results demonstrate that the new kernel performs similarly well as the negative distance kernel in gradient descent methods, but now with theoretical guarantees. - Open Access
HOT-POT: Optimal Transport for Sparse Stereo Matching
Stereo vision between images faces a range of challenges, including occlusions, motion, and camera distortions, across applications in autonomous driving, robotics, and face analysis. Due to parameter sensitivity, further complications arise for stereo matching with sparse features, such as facial landmarks. To overcome this ill-posedness and enable unsupervised sparse matching, we consider line constraints of the camera geometry from an optimal transport (OT) viewpoint. Formulating camera-projected points as (half)lines, we propose the use of the classical epipolar distance as well as a 3D ray distance to quantify matching quality. Employing these distances as a cost function of a (partial) OT problem, we arrive at efficiently solvable assignment problems. Moreover, we extend our approach to unsupervised object matching by formulating it as a hierarchical OT problem. The resulting algorithms allow for efficient feature and object matching, as demonstrated in our numerical experiments. Here, we focus on applications in facial analysis, where we aim to match distinct landmarking conventions.
Open AccessHOT-POT: Optimal Transport for Sparse Stereo Matching
Stereo vision between images faces a range of challenges, including occlusions, motion, and camera distortions, across applications in autonomous driving, robotics, and face analysis. Due to parameter sensitivity, further complications arise for stereo matching with sparse features, such as facial landmarks. To overcome this ill-posedness and enable unsupervised sparse matching, we consider line constraints of the camera geometry from an optimal transport (OT) viewpoint. Formulating camera-projected points as (half)lines, we propose the use of the classical epipolar distance as well as a 3D ray distance to quantify matching quality. Employing these distances as a cost function of a (partial) OT problem, we arrive at efficiently solvable assignment problems. Moreover, we extend our approach to unsupervised object matching by formulating it as a hierarchical OT problem. The resulting algorithms allow for efficient feature and object matching, as demonstrated in our numerical experiments. Here, we focus on applications in facial analysis, where we aim to match distinct landmarking conventions.
- Open Access
On Coorbit Fréchet Spaces
This paper is concerned with a new approach to coorbit space theory. Usually, coorbit spaces are defined by collecting all distributions for which the voice transform associated with a square-integrable group representation possesses a certain decay, usually measured in a Banach space norm such as weighted $L_p$-norms. Unfortunately, in cases where the representation does not satisfy certain integrability conditions, one is faced with a bottleneck, namely that the discretization of the coorbit spaces is surprisingly difficult. It turns out that in these cases the construction of coorbit spaces as Fréchet spaces is much more convenient since then atomic decompositions can be established in a very natural way.
Open AccessOn Coorbit Fréchet Spaces
This paper is concerned with a new approach to coorbit space theory. Usually, coorbit spaces are defined by collecting all distributions for which the voice transform associated with a square-integrable group representation possesses a certain decay, usually measured in a Banach space norm such as weighted $L_p$-norms. Unfortunately, in cases where the representation does not satisfy certain integrability conditions, one is faced with a bottleneck, namely that the discretization of the coorbit spaces is surprisingly difficult. It turns out that in these cases the construction of coorbit spaces as Fréchet spaces is much more convenient since then atomic decompositions can be established in a very natural way.
- Open Access
Stochastic Zeroth-Order Method for Computing Generalized Rayleigh Quotients
The maximization of the (generalized) Rayleigh quotient is a central problem in numerical linear algebra. Conventional algorithms for its computation typically rely on matrix-adjoint products, making them sensitive to errors arising from adjoint mismatches. To address this issue, we introduce a stochastic zeroth-order Riemannian algorithm that maximizes the generalized Rayleigh quotient without requiring adjoint or matrix inverse computations. We provide theoretical convergence guarantees showing that the iterates converge to the set of global maximizers of the (generalized) Rayleigh quotient at a sublinear rate with probability one. Our theoretical results are supported by numerical experiments, which demonstrate the excellent performance of the proposed method compared to state-of-the-art algorithms.
Open AccessStochastic Zeroth-Order Method for Computing Generalized Rayleigh Quotients
The maximization of the (generalized) Rayleigh quotient is a central problem in numerical linear algebra. Conventional algorithms for its computation typically rely on matrix-adjoint products, making them sensitive to errors arising from adjoint mismatches. To address this issue, we introduce a stochastic zeroth-order Riemannian algorithm that maximizes the generalized Rayleigh quotient without requiring adjoint or matrix inverse computations. We provide theoretical convergence guarantees showing that the iterates converge to the set of global maximizers of the (generalized) Rayleigh quotient at a sublinear rate with probability one. Our theoretical results are supported by numerical experiments, which demonstrate the excellent performance of the proposed method compared to state-of-the-art algorithms.
- 19 July 2025
- Published by Springer Nature
- p. 185-254
Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans
- 19 July 2025
- Published by Springer Nature
- p. 185-254
Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans
- Open Access
Unsupervised Ground Metric Learning
Data classification without access to labeled samples remains a challenging problem. It usually depends on an appropriately chosen distance between features, a topic addressed in metric learning. Recently, Huizing, Cantini and Peyré proposed to simultaneously learn optimal transport (OT) cost matrices between samples and features of the dataset. This leads to the task of finding positive eigenvectors of a certain nonlinear function that maps cost matrices to OT distances. Having this basic idea in mind, we consider both the algorithmic and the modeling part of unsupervised metric learning. First, we examine appropriate algorithms and their convergence. In particular, we propose to use the stochastic random function iteration algorithm and prove that it converges linearly for our setting, although our operators are not paracontractive as it was required for convergence so far. Second, we ask the natural question if the OT distance can be replaced by other distances. We show how Mahalanobis-like distances fit into our considerations. Further, we examine an approach via graph Laplacians. In contrast to the previous settings, we have just to deal with linear functions in the wanted matrices here, so that simple algorithms from linear algebra can be applied.
Open AccessUnsupervised Ground Metric Learning
Data classification without access to labeled samples remains a challenging problem. It usually depends on an appropriately chosen distance between features, a topic addressed in metric learning. Recently, Huizing, Cantini and Peyré proposed to simultaneously learn optimal transport (OT) cost matrices between samples and features of the dataset. This leads to the task of finding positive eigenvectors of a certain nonlinear function that maps cost matrices to OT distances. Having this basic idea in mind, we consider both the algorithmic and the modeling part of unsupervised metric learning. First, we examine appropriate algorithms and their convergence. In particular, we propose to use the stochastic random function iteration algorithm and prove that it converges linearly for our setting, although our operators are not paracontractive as it was required for convergence so far. Second, we ask the natural question if the OT distance can be replaced by other distances. We show how Mahalanobis-like distances fit into our considerations. Further, we examine an approach via graph Laplacians. In contrast to the previous settings, we have just to deal with linear functions in the wanted matrices here, so that simple algorithms from linear algebra can be applied.