PuSH - Publikationsserver des Helmholtz Zentrums München

Becker, S. ; Klein, M. ; Neitz, A.* ; Parascandolo, G.* ; Kilbertus, N.

Predicting ordinary differential equations with transformers.

In: (Proceedings of Machine Learning Research). 1269 Law St, San Diego, Ca, United States: Jmlr-journal Machine Learning Research, 2023. 25 ( ; 202)
We develop a transformer-based sequence-to-sequence model that recovers scalar ordinary differential equations (ODEs) in symbolic form from irregularly sampled and noisy observations of a single solution trajectory. We demonstrate in extensive empirical evaluations that our model performs better or on par with existing methods in terms of accurate recovery across various settings. Moreover, our method is efficiently scalable: after one-time pretraining on a large set of ODEs, we can infer the governing law of a new observed solution in a few forward passes of the model.
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
ISSN (print) / ISBN 2640-3498
Konferenztitel Proceedings of Machine Learning Research
Quellenangaben Band: 202, Heft: , Seiten: 25 Artikelnummer: , Supplement: ,
Verlag Jmlr-journal Machine Learning Research
Verlagsort 1269 Law St, San Diego, Ca, United States
Nichtpatentliteratur Publikationen
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Institute of Computational Biology (ICB)
Förderungen Helmholtz Association's Initiative and Networking Fund on the HAICORE@FZJpartition
Helmholtz Association under the joint research school "Munich School for Data Science - MUDS"