Research

Posted on: Thu 15 October 2026

Preprint

J. Cribeiro-Ramallo, F. Kalinke, and Z. Szabó. Unbounded Characteristic and Universal Kernels. Preprint, 2026.
paper (arXiv)

F. Matteucci and F. Kalinke. Conditional Kernel Stein Discrepancy. Preprint, 2026.
paper (arXiv) | code

J. Cribeiro-Ramallo, F. Kalinke, and Z. Szabó. Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD. Preprint, 2026.
paper (arXiv)

F. Kalinke, Z. Szabó, and B. K. Sriperumbudur. Nyström Kernel Stein Discrepancy Tests. Preprint, 2026.
paper (arXiv) | code

T. Fuchs, F. Kalinke, and N. Klein. QDSB: Quantized Diffusion Schrödinger Bridges. Preprint, 2026.
paper (arXiv) | code

2026

P. Roudaki, S. Gavioli-Akilagun, F. Kalinke, M. Azadkia, and Z. Szabó. Kernel Integrated R^2: A Measure of Dependence. Conference on Uncertainty in Artificial Intelligence (UAI), pp. 5764–5789, 2026.
paper (arXiv) | paper (UAI) | code

J. Cribeiro-Ramallo, A. Aich, F. Kalinke, A. B. Aich, and Z. Szabó. The Minimax Lower Bound of Kernel Stein Discrepancy Estimation. International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 901–909, 2026.
paper (arXiv) | paper (AISTATS)

2025

F. Kalinke* and S. Gavioli-Akilagun* (*Equal contribution). Optimal Online Change Detection via Random Fourier Features. Advances in Neural Information Processing Systems (NeurIPS), pp. 9866–9901, 2025.
paper (arXiv) | paper (NeurIPS) | paper (OpenReview) | poster | code

F. Kalinke. Kernel-based information theoretical measures: accelerations and limits. Dissertation, Karlsruhe Institute of Technology, 2025.
dissertation (KITopen)

T. Fuchs and F. Kalinke. Partial-Label Learning with Conformal Candidate Cleaning. Conference on Uncertainty in Artificial Intelligence (UAI), pp. 1337–1357, 2025.
paper (arXiv) | paper (UAI) | code

T. Fuchs and F. Kalinke. Robust Partial-Label Learning by Leveraging Class Activation Values. Machine Learning 114(8):193, 2025.
paper (arXiv) | paper (Springer) | paper (Springer Link (OA)) | code

F. Kalinke, Z. Szabó, and B. K. Sriperumbudur. Nyström Kernel Stein Discrepancy. International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 388–396, 2025.
paper (arXiv) | paper (AISTATS) | paper (OpenReview) | poster | code

F. Kalinke, M. Heyden, G. Gntuni, E. Fouché, and K. Böhm. Maximum Mean Discrepancy on Exponential Windows for Online Change Detection. Transactions on Machine Learning Research, 2025.
paper (arXiv) | paper (OpenReview) | code

T. Fuchs, F. Kalinke, and K. Böhm. Partial-Label Learning with a Reject Option. Transactions on Machine Learning Research, 2025.
paper (arXiv) | paper (OpenReview) | code

2024

F. Kalinke and Z. Szabó. The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels. Advances in Neural Information Processing Systems (NeurIPS), pp. 108468–108489, 2024.
paper (arXiv) | paper (NeurIPS) | paper (OpenReview) | poster

M. Heyden, E. Fouché, V. Arzamasov, T. Fenn, F. Kalinke, and K. Böhm. Adaptive Bernstein change detector for high-dimensional data streams. Data Mining and Knowledge Discovery 38(3):1334–1363, 2024.
paper (arXiv) | paper (author version) | paper (Springer) | code

2023

F. Kalinke, E. Fouché, H. Thiessen, and K. Böhm. Multi-kernel Times Series Outlier Detection. International Conference on Discovery Science (DS), pp. 688–702, 2023.
paper (author version) | paper (Springer) | slides | code

2021

F. Kalinke, P. Bielski, S. Singh, E. Fouché, and K. Böhm. An Evaluation of NILM Approaches on Industrial Energy-Consumption Data. International Conference on Future Energy Systems (e-Energy), pp. 239–243, 2021.
paper (ACM) | data

E. Fouché, F. Kalinke, and K. Böhm. Efficient subspace search in data streams. Information Systems 97:101705, 2021.
paper (arXiv) | paper (Elsevier) | code

E. Fouché, A. Mazankiewicz, F. Kalinke, and K. Böhm. A framework for dependency estimation in heterogeneous data streams. Distributed and Parallel Databases 39(2):415–444, 2021.
paper (Springer) | code

Category: misc