collaborators

5 papers

cs.LG2025

SensLI: Sensitivity-Based Layer Insertion for Neural Networks

Leonie Kreis, Evelyn Herberg, Frederik Köhne +2

The training of neural networks requires tedious and often manual tuning of the network architecture. We propose a systematic approach to inserting new layers during the training p…

stat.ML2025

An Exponential Averaging Process with Strong Convergence Properties

Frederik Köhne, Anton Schiela

Averaging, or smoothing, is a fundamental approach to obtain stable, de-noised estimates from noisy observations. In certain scenarios, observations made along trajectories of rand…

math.OC2024

Adaptive Step Sizes for Preconditioned Stochastic Gradient Descent

Frederik Köhne, Leonie Kreis, Anton Schiela +1

This paper proposes a novel approach to adaptive step sizes in stochastic gradient descent (SGD) by utilizing quantities that we have identified as numerically traceable -- the Lip…

math.FA2024

Nonlinear Fenchel Conjugates

Anton Schiela, Roland Herzog, Ronny Bergmann

The classical concept of Fenchel conjugation is tailored to extended real-valued functions defined on linear spaces. In this paper we generalize this concept to functions defined o…

math.DS2024

-error bounds for approximations of the Koopman operator by kernel extended dynamic mode decomposition

Frederik Köhne, Friedrich M. Philipp, Manuel Schaller +2

Extended dynamic mode decomposition (EDMD) is a well-established method to generate a data-driven approximation of the Koopman operator for analysis and prediction of nonlinear dyn…