Research Group Steffen Schneider
Steffen Schneider
leads the Dynamical Inference Lab at Helmholtz Munich.
He is working on machine learning algorithms for representation learning and inference of nonlinear system dynamics. His team applies these algorithms to model complex biological systems in neuroscience, cell biology and other life science applications.
Team members @MCML
PhD Students
Rodrigo Gonzalez Laiz
A3 | Computational Models
→ Group Steffen Schneider
Dynamical Inference
Tobias Schmidt
A3 | Computational Models
→ Group Steffen Schneider
Dynamical Inference
Publications @MCML
2025
Self-supervised contrastive learning performs non-linear system identification.
ICLR 2025 - 13th International Conference on Learning Representations. Singapore, Apr 24-28, 2025. To be published. Preprint available. URL
Abstract
Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal structure and auxiliary variables ensure that latent representations are related to the true underlying generative factors of the data. Here, we deepen this connection and show that SSL can perform system identification in latent space. We propose DynCL, a framework to uncover linear, switching linear and non-linear dynamics under a non-linear observation model, give theoretical guarantees and validate them empirically.
MCML Authors
©all images: LMU | TUM