Consistent Long-Term Forecasting of Ergodic Dynamical Systems

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.

References in corpus (7)

• Statistical Inference for Generative Models with Maximum Mean Discrepancy
• Modern Koopman Theory for Dynamical Systems
• Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces
• Optimal Rates for Regularized Conditional Mean Embedding Learning
• Koopman Kernel Regression
• Sharp Spectral Rates for Koopman Operator Learning
• Estimating Koopman operators with sketching to provably learn large scale dynamical systems