25 citations · 58 across the 16 of their papers we have counts for
17 papers
Asymptotic e-processes
Pierre-François Massiani, Sebastian Schulze, Mattes Mollenhauer
We investigate the concept of an asymptotic e-process, which is a doubly-indexed stochastic process that possesses, asymptotically for an approximati…
Float8@2bits: Entropy Coding Enables Data-Free Model Compression
Patrick Putzky, Martin Genzel, Mattes Mollenhauer +3
Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibi…
Fuk-Nagaev inequality in smooth Banach spaces: Optimum bounds for distributions of heavy-tailed martingales
Mattes Mollenhauer, Christian Fiedler
We derive a Fuk-Nagaev inequality for the maxima of norms of martingale sequences in smooth Banach spaces which allow for a finite number of higher conditional moments. The bound i…
Regularized least squares learning with heavy-tailed noise is minimax optimal
Mattes Mollenhauer, Nicole Mücke, Dimitri Meunier +1
This paper examines the performance of ridge regression in reproducing kernel Hilbert spaces in the presence of noise that exhibits a finite number of higher moments. We establish…
Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation
Martin Genzel, Patrick Putzky, Pengfei Zhao +5
The adoption of Foundation Models in resource-constrained environments remains challenging due to their large size and inference costs. A promising way to overcome these limitation…
Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
Dimitri Meunier, Zikai Shen, Mattes Mollenhauer +2
We study theoretical properties of a broad class of regularized algorithms with vector-valued output. These spectral algorithms include kernel ridge regression, kernel principal co…
Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithm
Zhu Li, Dimitri Meunier, Mattes Mollenhauer +1
We present the first optimal rates for infinite-dimensional vector-valued ridge regression on a continuous scale of norms that interpolate between and the hypothesis space, w…
On the concentration of subgaussian vectors and positive quadratic forms in Hilbert spaces
Mattes Mollenhauer, Claudia Schillings
In these notes, we investigate the tail behaviour of the norm of subgaussian vectors in a Hilbert space. The subgaussian variance proxy is given as a trace class operator, allowing…
Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problem
Mattes Mollenhauer, Nicole Mücke, T. J. Sullivan
We consider the problem of learning a linear operator between two Hilbert spaces from empirical observations, which we interpret as least squares regression in infinite dimensi…
Optimal Rates for Regularized Conditional Mean Embedding Learning
Zhu Li, Dimitri Meunier, Mattes Mollenhauer +1
We address the consistency of a kernel ridge regression estimate of the conditional mean embedding (CME), which is an embedding of the conditional distribution of given int…
Optimal Reaction Coordinates: Variational Characterization and Sparse Computation
Andreas Bittracher, Mattes Mollenhauer, Péter Koltai +1
Reaction Coordinates (RCs) are indicators of hidden, low-dimensional mechanisms that govern the long-term behavior of high-dimensional stochastic processes. We present a novel and…
Nonparametric approximation of conditional expectation operators
Mattes Mollenhauer, Péter Koltai
Given the joint distribution of two random variables on some second countable locally compact Hausdorff space, we investigate the statistical approximation of the -opera…
Kernel Autocovariance Operators of Stationary Processes: Estimation and Convergence
Mattes Mollenhauer, Stefan Klus, Christof Schütte +1
We consider autocovariance operators of a stationary stochastic process on a Polish space that is embedded into a reproducing kernel Hilbert space. We investigate how empirical est…
Kernel Conditional Density Operators
Ingmar Schuster, Mattes Mollenhauer, Stefan Klus +1
We introduce a novel conditional density estimation model termed the conditional density operator (CDO). It naturally captures multivariate, multimodal output densities and shows p…
Kernel methods for detecting coherent structures in dynamical data
Stefan Klus, Brooke E. Husic, Mattes Mollenhauer +1
We illustrate relationships between classical kernel-based dimensionality reduction techniques and eigendecompositions of empirical estimates of reproducing kernel Hilbert space (R…
Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces
Mattes Mollenhauer, Ingmar Schuster, Stefan Klus +1
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…
On Hyperparameter Search in Cluster Ensembles
Luzie Helfmann, Johannes von Lindheim, Mattes Mollenhauer +1
Quality assessments of models in unsupervised learning and clustering verification in particular have been a long-standing problem in the machine learning research. The lack of rob…