Course Correcting Koopman Representations
Not on the map. Why?
Abstract (arXiv)
Koopman representations aim to learn features of nonlinear dynamical systems (NLDS) which lead to linear dynamics in the latent space. Theoretically, such features can be used to simplify many problems in modeling and control of NLDS. In this work we study autoencoder formulations of this problem, and different ways they can be used to model dynamics, specifically for future state prediction over long horizons. We discover several limitations of predicting future states in the latent space and propose an inference-time mechanism, which we refer to as Periodic Reencoding, for faithfully capturing long term dynamics. We justify this method both analytically and empirically via experiments in low and high dimensional NLDS.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 19 of its 36 references that are in the map. First posted on arXiv 23 Oct 2023.
Builds on
19 of 36 references.
References · 19
- 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
- 2017Decoupled Weight Decay Regularizationcited by 1,831
- 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,427
- 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
- 2022Simplified State Space Layers for Sequence Modelingcited by 788
- 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
- 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
- 2023Resurrecting Recurrent Neural Networks for Long Sequencescited by 408
- 2015Unitary Evolution Recurrent Neural Networkscited by 294
- 2021Modern Koopman Theory for Dynamical Systemscited by 276
- 2017Parallelizing Linear Recurrent Neural Nets Over Sequence Lengthcited by 127
7 more
- 2020Forecasting Sequential Data using Consistent Koopman Autoencoderscited by 115
- 2020Multiscale Simulations of Complex Systems by Learning their Effective Dynamicscited by 86
- 2018Deep Dynamical Modeling and Control of Unsteady Fluid Flowscited by 68
- 2021On the difficulty of learning chaotic dynamics with RNNscited by 67
- 2015Synthesis of recurrent neural networks for dynamical system simulationcited by 16
- 2023Task-Oriented Koopman-Based Control with Contrastive Encodercited by 8
- 2023Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Datacited by 5
Built on by
Citing papers per year: 2026: 2.
2 papers.