Demo Data from EDBT 2026 / reviewers in the wild / expert
Alexander Valentinitsch
dblp:86/9222
· DBLP profile ↗
5ranked-venue papers
0as first author
3since 2021 · last 2026
0000-0003-3348-6302ORCID · corroborated
Domains — the database's venue-derived domains; a paper can count in several
Graphics, computer vision, multimedia, augmented reality and games · 3 · 1 since 2021Applied, interdisciplinary, general and emerging computing · 3 · 1 since 2021Artificial intelligence and machine learning · 2 · 2 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
1 paper |
Efficient and distributed learning · 50% Learning theory · 25% Kernel, tree and ensemble methods · 25% | |
| Theoretical computer science
1 paper |
Mathematical optimization · 100% |
Topics — the 5 heaviest of 5, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Efficient and distributed learning
collaborative learning |
1.0 | 1 | 2026 | Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint) · AAAI 2026 |
Machine learning › Efficient and distributed learning
federated learning |
1.0 | 1 | 2026 | Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint) · AAAI 2026 |
Machine learning › Learning theory
generalization bounds |
1.0 | 1 | 2026 | Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint) · AAAI 2026 |
Machine learning › Kernel, tree and ensemble methods › kernel methods › kernel machines
kernel machine generalization |
1.0 | 1 | 2026 | Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint) · AAAI 2026 |
Mathematical optimization › continuous optimization
convex optimization |
0.3 | 1 | 2026 | Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint) · AAAI 2026 |
Methods — techniques the papers use, named apart from their topics
reproducing kernel hilbert space · 2.0convex optimization · 2.0kernel machines · 1.0kernel machine · 1.0
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2026 | Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint)abstractThis paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For classification problems, this approach allows us to learn bounded geometric structures around given data points and hence solve the global model learning problem in an efficient way by exploiting convexity properties of the related optimisation problem in a Reproducing Kernel Hilbert Space (RKHS). In this way, we can reduce classification problems to determining the closest bounded geometric structure from a given data point. Further advantages that come with our solution is that our approach does not require clients to perform multiple epochs of local optimisation using stochastic gradient descent, nor require rounds of communication between client/server for optimising the global model. We highlight that numerous experiments have shown that the proposed method is a competitive alternative to the state-of-the-art. Mohit Kumar 0001, Alexander Valentinitsch, Magdalena Fuchs, Mathias Brucker, Juliana Küster Filipe Bowles, Adnan Husakovic, Bernhard Moser 0001 |
AAAI | 2 |
| 2025 | Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient DescentabstractThis paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For classification problems, this approach allows us to learn bounded geometric structures around given data points and hence solve the global model learning problem in an efficient way by exploiting convexity properties of the related optimisation problem in a Reproducing Kernel Hilbert Space (RKHS). In this way, we can reduce classification problems to determining the closest bounded geometric structure from a given data point. Further advantages that come with our solution is that our approach does not require clients to perform multiple epochs of local optimisation using stochastic gradient descent, nor require rounds of communication between client/server for optimising the global model. We highlight that numerous experiments have shown that the proposed method is a competitive alternative to the state-of-the-art. Mohit Kumar 0001, Alexander Valentinitsch, Magdalena Fuchs, Mathias Brucker, Juliana Küster Filipe Bowles, Adnan Husakovic, Bernhard Moser 0001 |
J. Artif. Intell. Res. | 2 |
| 2021 | VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images
Anjany Sekuboyina, Malek El Husseini, Amirhossein Bayat, Maximilian Löffler, Hans Liebl, Hongwei Li 0004, Giles Tetteh, Jan Kukacka, Christian Payer, Darko Stern, Martin Urschler, Maodong Chen, Dalong Cheng, Nikolas Leßmann, Yujin Hu, Tianfu Wang 0001, Dong Yang 0005, Daguang Xu, Felix Ambellan, Tamaz Amiranashvili, Moritz Ehlke, Hans Lamecker, Sebastian Lehnert, Marilia Lirio, Nicolás Pérez de Olaguer, Heiko Ramm, Manish Sahu, Alexander Tack, Stefan Zachow, Xinjun Ma, Christoph Angerman, Xin Wang 0113, Alexandre Kirszenberg, Élodie Puybareau, Yiwei Bai, Brandon H. Rapazzo, Timyoas Yeah, Amber Zhang, Shangliang Xu, Feng Hou, Zhiqiang He 0002, Chan Zeng, Zheng Xiangshang, Xu Liming, Tucker J. Netherton, Raymond P. Mumme, Laurence E. Court, Zixun Huang, Chenhang He, Li-Wen Wang, Sai-Ho Ling, Lê Duy Huynh, Nicolas Boutry, Roman Jakubícek, Jirí Chmelík, Supriti Mulay, Mohanasankar Sivaprakasam, Johannes C. Paetzold, Suprosanna Shit, Ivan Ezhov, Benedikt Wiestler, Ben Glocker, Alexander Valentinitsch, Markus Rempfler, Bjoern Menze, Jan Kirschke |
Medical Image Anal. | 66 |
| 2019 | Probabilistic Point Cloud Reconstructions for Vertebral Shape Analysis
Anjany Sekuboyina, Markus Rempfler, Alexander Valentinitsch, Maximilian Löffler, Jan Kirschke, Bjoern Menze |
MICCAI (6) | 3 |
| 2018 | Btrfly Net: Vertebrae Labelling with Energy-Based Adversarial Learning of Local Spine Prior
Anjany Sekuboyina, Markus Rempfler, Jan Kukacka, Giles Tetteh, Alexander Valentinitsch, Jan Kirschke, Bjoern Menze |
MICCAI (4) | 5 |