Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 91 tok/s
Gemini 2.5 Pro 56 tok/s Pro
GPT-5 Medium 29 tok/s Pro
GPT-5 High 29 tok/s Pro
GPT-4o 108 tok/s Pro
Kimi K2 214 tok/s Pro
GPT OSS 120B 470 tok/s Pro
Claude Sonnet 4 40 tok/s Pro
2000 character limit reached

Consistent Long-Term Forecasting of Ergodic Dynamical Systems (2312.13426v1)

Published 20 Dec 2023 in stat.ML, cs.LG, and math.DS

Abstract: We study the evolution of distributions under the action of an ergodic dynamical system, which may be stochastic in nature. By employing tools from Koopman and transfer operator theory one can evolve any initial distribution of the state forward in time, and we investigate how estimators of these operators perform on long-term forecasting. Motivated by the observation that standard estimators may fail at this task, we introduce a learning paradigm that neatly combines classical techniques of eigenvalue deflation from operator theory and feature centering from statistics. This paradigm applies to any operator estimator based on empirical risk minimization, making them satisfy learning bounds which hold uniformly on the entire trajectory of future distributions, and abide to the conservation of mass for each of the forecasted distributions. Numerical experiments illustrates the advantages of our approach in practice.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Operator-theoretic framework for forecasting nonlinear time series with kernel analog techniques. Physica D: Nonlinear Phenomena, 409:132520, 2020.
  2. Ergodic theory, dynamic mode decomposition, and computation of spectral properties of the koopman operator. SIAM Journal on Applied Dynamical Systems, 16(4):2096–2126, 2017.
  3. Ludwig Arnold. Stochastic Differential Equations: Theory and Applications, volume 2. John Wiley & Sons, 1974.
  4. Nachman Aronszajn. Theory of reproducing kernels. Transactions of the American Mathematical Society, 68(3):337–404, 1950.
  5. Forecasting sequential data using consistent koopman autoencoders. In Proceedings of the 37th International Conference on Machine Learning, volume 119, pages 475–485. PMLR, 2020.
  6. Oscar F. Bandtlow. Estimates for norms of resolvents and an application to the perturbation of spectra. Mathematische Nachrichten, 267, 2004.
  7. KoopmanizingFlows: Diffeomorphically Learning Stable Koopman Operators. arXiv preprint arXiv.2112.04085, 2021.
  8. Koopman kernel regression. arXiv preprint arXiv:2305.16215, 2023.
  9. Kernel Methods for the Approximation of Nonlinear Systems. SIAM Journal on Control and Optimization, 55(4):2460–2492, 2017.
  10. Statistical inference for generative models with maximum mean discrepancy. arXiv preprint arXiv:1906.05944, 2019.
  11. Modern Koopman Theory for Dynamical Systems. SIAM Review, 64(2):229–340, 2022.
  12. Applied Koopmanism. Chaos: An Interdisciplinary Journal of Nonlinear Science, 22(4):047510, 2012.
  13. Optimal rates for the regularized least-squares algorithm. Foundations of Computational Mathematics, 7(3):331–368, 2007.
  14. A theory of the term structure of interest rates. Econometrica, 53(2):385, 1985.
  15. G. Da Prato and J. Zabczyk. Ergodicity for Infinite Dimensional Systems. London Mathematical Society Lecture Note Series. Cambridge University Press, 1996.
  16. Koopman spectra in reproducing kernel Hilbert spaces. Applied and Computational Harmonic Analysis, 49(2):573–607, 2020.
  17. New langevin and gradient thermostats for rigid body dynamics. The Journal of Chemical Physics, 142(14):144114, 2015.
  18. Extremal growth of powers of operators satisfying resolvent conditions of kreiss-ritt type. Journal of Functional Analysis, 196(1):135–154, 2002.
  19. Learning Stable Koopman Embeddings. arXiv preprint arXiv.2110.06509, 2021.
  20. Sobolev norm learning rates for regularized least-squares algorithms. Journal of Machine Learning Research, 21(205):1–38, 2020.
  21. Hans Hersbach. Decomposition of the continuous ranked probability score for ensemble prediction systems. Weather and Forecasting, 15(5):559–570, October 2000.
  22. Sparse learning of dynamical systems in RKHS: An operator-theoretic approach. In Proceedings of the 40th International Conference on Machine Learning, volume 202, pages 13325–13352. PMLR, 2023.
  23. A rigorous theory of conditional mean embeddings. SIAM Journal on Mathematics of Data Science, 2(3):583–606, 2020.
  24. Data-driven model reduction and transfer operator approximation. Journal of Nonlinear Science, 28(3):985–1010, 2018.
  25. Eigendecompositions of transfer operators in reproducing kernel Hilbert spaces. Journal of Nonlinear Science, 30(1):283–315, 2019.
  26. Sharp spectral rates for koopman operator learning. arXiv:2302.02004v3, 2023.
  27. Learning dynamical systems via Koopman operator regression in reproducing kernel hilbert spaces. In Advances in Neural Information Processing Systems, 2022.
  28. Dynamic Mode Decomposition. Society for Industrial and Applied Mathematics, 2016.
  29. Chaos, Fractals, and Noise, volume 97 of Applied Mathematical Sciences. Springer New York, 1994.
  30. Optimal rates for regularized conditional mean embedding learning. In Advances in Neural Information Processing Systems, 2022.
  31. Deep learning for universal linear embeddings of nonlinear dynamics. Nature Communications, 9(1), 2018.
  32. Estimating koopman operators with sketching to provably learn large scale dynamical systems. arXiv:2306.04520, 2023.
  33. Igor Mezić. Analysis of fluid flows via spectral properties of the koopman operator. Annual Review of Fluid Mechanics, 45:357–378, 2013.
  34. A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model. Applied Energy, 232:229–244, 2018.
  35. Deep dynamical modeling and control of unsteady fluid flows. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, page 9278–9288, 2018.
  36. Kernel Mean Embedding of Distributions: A Review and Beyond. Foundations and Trends® in Machine Learning, 10(1-2):1–141, 2017.
  37. Andrea Pascucci. PDE and Martingale Methods in Option Pricing. Springer Milan, 2011.
  38. Discovering dynamic patterns from infectious disease data using dynamic mode decomposition. International health, 7(2):139–145, 2015.
  39. Yousef Saad. Numerical Methods for Large Eigenvalue Problems: Revised Edition. Classics in Applied Mathematics, SIAM, 2011.
  40. Sebastian Scher. Toward data-driven weather and climate forecasting: Approximating a simple general circulation model with deep learning. Geophysical Research Letters, 45(22):12–616, 2018.
  41. Transfer Operator Approach to Conformational Dynamics in Biomolecular Systems. In Ergodic Theory, Analysis, and Efficient Simulation of Dynamical Systems, pages 191–223. Springer Berlin Heidelberg, 2001.
  42. Support Vector Machines. Springer New York, 2008.
  43. Spectra and Pseudospectra: The Behavior of Nonnormal Matrices and Operators. Princeton University Press, 2020.
  44. Oldrich Vasicek. An equilibrium characterization of the term structure. Journal of Financial Economics, 5(2):177–188, 1977.
  45. A kernel-based method for data-driven Koopman spectral analysis. Journal of Computational Dynamics, 2(2):247–265, 2015.
  46. J. Zabczyk. Mathematical Control Theory: An Introduction. Systems & Control: Foundations & Applications. Springer International Publishing, 2020.
Citations (4)
View on Semantic Scholar
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-Up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now