Paul Schwerdtner

2 accepted papers

2026

Two-Parameter Flows for Learning Population Dynamics of Physical Systems

Paul Schwerdtner, Tobias Blickhan, Benjamin Peherstorfer

ICML 2026poster

This work addresses the problem of learning the dynamics of high-dimensional probability densities over time using unlabeled samples, without assuming access to trajectory information. We introduce two-parameter flows that learn only sampling-time transports from a base distribution to each marginal…

Cited by 0 Source ↗Scholar ↗

2025

Hankel Singular Value Regularization for Highly Compressible State Space Models

Paul Schwerdtner, Jules Berman, Benjamin Peherstorfer

NeurIPS 2025poster

Deep neural networks using state space models as layers are well suited for long-range sequence tasks but can be challenging to compress after training. We use that regularizing the sum of Hankel singular values of state space models leads to a fast decay of these singular values and thus to compres…

Cited by 0 Source ↗Scholar ↗