000276091 001__ 276091
000276091 005__ 20250121165738.0
000276091 037__ $$aDZNE-2025-00172
000276091 1001_ $$0P:(DE-2719)9001044$$aLagemann, Kai$$b0$$eFirst author$$udzne
000276091 1112_ $$a12th International Conference on Learning Representations$$cVienna$$d2024-05-07 - 2024-05-11$$gICLR 2024$$wAustria
000276091 245__ $$aINVARIANCE-BASED LEARNING OF LATENT DYNAMICS
000276091 260__ $$c2024
000276091 300__ $$a200372
000276091 3367_ $$2ORCID$$aCONFERENCE_PAPER
000276091 3367_ $$033$$2EndNote$$aConference Paper
000276091 3367_ $$2BibTeX$$aINPROCEEDINGS
000276091 3367_ $$2DRIVER$$aconferenceObject
000276091 3367_ $$2DataCite$$aOutput Types/Conference Paper
000276091 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1737452533_5211
000276091 520__ $$aWe propose a new model class aimed at predicting dynamical trajectories from highdimensional empirical data. This is done by combining variational autoencodersand (spatio-)temporal transformers within a framework designed to enforce certainscientifically-motivated invariances. The models allow inference of system behavior at any continuous time and generalization well beyond the data distributionsseen during training. Furthermore, the models do not require an explicit neuralODE formulation, making them efficient and highly scalable in practice. We studybehavior through simple theoretical analyses and extensive empirical experiments.The latter investigate the ability to predict the trajectories of complicated systemsbased on finite data and show that the proposed approaches can outperform existingneural-dynamical models. We study also more general inductive bias in the contextof transfer to data obtained under entirely novel system interventions. Overall, ourresults provide a new framework for efficiently learning complicated dynamics in adata-driven manner, with potential applications in a wide range of fields includingphysics, biology, and engineering.
000276091 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0
000276091 7001_ $$0P:(DE-HGF)0$$aLagemann, Christian$$b1
000276091 7001_ $$0P:(DE-2719)2811372$$aMukherjee, Sach$$b2$$eLast author$$udzne
000276091 8564_ $$uhttps://openreview.net/forum?id=EWTFMkTdkT
000276091 8564_ $$uhttps://pub.dzne.de/record/276091/files/DZNE-2025-00172.pdf
000276091 8564_ $$uhttps://pub.dzne.de/record/276091/files/DZNE-2025-00172.pdf?subformat=pdfa$$xpdfa
000276091 909CO $$ooai:pub.dzne.de:276091$$pVDB
000276091 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9001044$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b0$$kDZNE
000276091 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2811372$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b2$$kDZNE
000276091 9131_ $$0G:(DE-HGF)POF4-354$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Prevention and Healthy Aging$$x0
000276091 9201_ $$0I:(DE-2719)1013030$$kAG Mukherjee$$lStatistics and Machine Learning$$x0
000276091 980__ $$acontrib
000276091 980__ $$aVDB
000276091 980__ $$aI:(DE-2719)1013030
000276091 980__ $$aUNRESTRICTED