TY - GEN
T1 - Forecasting sequential data using consistent koopman autoencoders
AU - Azencot, Omri
AU - Erichson, N. Benjamin
AU - Lin, Vanessa
AU - Mahoney, Michael W.
N1 - Publisher Copyright:
© ICML 2020. All rights reserved.
PY - 2020/1/1
Y1 - 2020/1/1
N2 - Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences. A new class of physics-based methods related to Koopman theory has been introduced, offering an alternative for processing nonlinear dynamical systems. In this work, we propose a novel Consistent Koopman Autoencoder model which, unlike the majority of existing work, leverages the forward and backward dynamics. Key to our approach is a new analysis which explores the interplay between consistent dynamics and their associated Koopman operators. Our network is directly related to the derived analysis, and its computational requirements are comparable to other baselines. We evaluate our method on a wide range of high-dimensional and short-Term dependent problems, and it achieves accurate estimates for significant prediction horizons, while also being robust to noise.
AB - Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences. A new class of physics-based methods related to Koopman theory has been introduced, offering an alternative for processing nonlinear dynamical systems. In this work, we propose a novel Consistent Koopman Autoencoder model which, unlike the majority of existing work, leverages the forward and backward dynamics. Key to our approach is a new analysis which explores the interplay between consistent dynamics and their associated Koopman operators. Our network is directly related to the derived analysis, and its computational requirements are comparable to other baselines. We evaluate our method on a wide range of high-dimensional and short-Term dependent problems, and it achieves accurate estimates for significant prediction horizons, while also being robust to noise.
UR - http://www.scopus.com/inward/record.url?scp=85105237081&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85105237081
T3 - 37th International Conference on Machine Learning, ICML 2020
SP - 452
EP - 462
BT - 37th International Conference on Machine Learning, ICML 2020
A2 - Daume, Hal
A2 - Singh, Aarti
PB - International Machine Learning Society (IMLS)
T2 - 37th International Conference on Machine Learning, ICML 2020
Y2 - 13 July 2020 through 18 July 2020
ER -