no code implementations • 12 Dec 2023 • Zhu Li, Dimitri Meunier, Mattes Mollenhauer, Arthur Gretton
We present the first optimal rates for infinite-dimensional vector-valued ridge regression on a continuous scale of norms that interpolate between $L_2$ and the hypothesis space, which we consider as a vector-valued reproducing kernel Hilbert space.
no code implementations • 16 Nov 2022 • Mattes Mollenhauer, Nicole Mücke, T. J. Sullivan
However, we prove that, in terms of spectral properties and regularisation theory, this inverse problem is equivalent to the known compact inverse problem associated with scalar response regression.
no code implementations • 2 Aug 2022 • Zhu Li, Dimitri Meunier, Mattes Mollenhauer, Arthur Gretton
We address the misspecified setting, where the target CME is in the space of Hilbert-Schmidt operators acting from an input interpolation space between $\mathcal{H}_X$ and $L_2$, to $\mathcal{H}_Y$.
no code implementations • 23 Dec 2020 • Mattes Mollenhauer, Péter Koltai
This also provides a novel perspective on which limiting object the nonparametric estimate of $P$ converges to.
no code implementations • 2 Apr 2020 • Mattes Mollenhauer, Stefan Klus, Christof Schütte, Péter Koltai
We consider autocovariance operators of a stationary stochastic process on a Polish space that is embedded into a reproducing kernel Hilbert space.
no code implementations • 27 May 2019 • Ingmar Schuster, Mattes Mollenhauer, Stefan Klus, Krikamol Muandet
The proposed model is based on a novel approach to the reconstruction of probability densities from their kernel mean embeddings by drawing connections to estimation of Radon-Nikodym derivatives in the reproducing kernel Hilbert space (RKHS).
no code implementations • 16 Apr 2019 • Stefan Klus, Brooke E. Husic, Mattes Mollenhauer, Frank Noé
In particular, we show that kernel canonical correlation analysis (CCA) can be interpreted in terms of kernel transfer operators and that it can be obtained by optimizing the variational approach for Markov processes (VAMP) score.
no code implementations • 24 Jul 2018 • Mattes Mollenhauer, Ingmar Schuster, Stefan Klus, Christof Schütte
Reproducing kernel Hilbert spaces (RKHSs) play an important role in many statistics and machine learning applications ranging from support vector machines to Gaussian processes and kernel embeddings of distributions.
no code implementations • 29 Mar 2018 • Luzie Helfmann, Johannes von Lindheim, Mattes Mollenhauer, Ralf Banisch
Quality assessments of models in unsupervised learning and clustering verification in particular have been a long-standing problem in the machine learning research.