Rodrigo González Laiz — accepted AI-conference papers

2025

Self-supervised contrastive learning performs non-linear system identification

Rodrigo González Laiz, Tobias Schmidt, Steffen Schneider

ICLR 2025poster

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 representat…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Time-series attribution maps with regularized contrastive learning

Steffen Schneider, Rodrigo González Laiz, Anastasiia Filippova, Markus Frey, Mackenzie W Mathis

AISTATS 2025poster

Gradient-based attribution methods aim to explain decisions of deep learning models but so far lack identifiability guarantees. Here, we propose a method to generate attribution maps with identifiability guarantees by developing a regularized contrastive learning algorithm trained on time-series dat…

Cited by 0 Source ↗code ↗Scholar ↗