Kostic, VR; Novelli, P; Lounici, K; Pontil, M; (2023) Sharp Spectral Rates for Koopman Operator Learning. In: Oh, Alice and Naumann, Tristan and Globerson, Amir and Saenko, Kate and Hardt, Moritz and Levine, Sergey, (eds.) Advances in Neural Information Processing Systems.

Preview

PDF 6738_sharp_spectral_rates_for_koopm.pdf - Published Version Download (1MB) | Preview

Abstract

Nonlinear dynamical systems can be handily described by the associated Koopman operator, whose action evolves every observable of the system forward in time.Learning the Koopman operator and its spectral decomposition from data is enabled by a number of algorithms.In this work we present for the first time non-asymptotic learning bounds for the Koopman eigenvalues and eigenfunctions.We focus on time-reversal-invariant stochastic dynamical systems, including the important example of Langevin dynamics.We analyze two popular estimators: Extended Dynamic Mode Decomposition (EDMD) and Reduced Rank Regression (RRR).Our results critically hinge on novel minimax estimation bounds for the operator norm error, that may be of independent interest.Our spectral learning bounds are driven by the simultaneous control of the operator norm error and a novel metric distortion functional of the estimated eigenfunctions.The bounds indicates that both EDMD and RRR have similar variance, but EDMD suffers from a larger bias which might be detrimental to its learning rate.Our results shed new light on the emergence of spurious eigenvalues, an issue which is well known empirically.Numerical experiments illustrate the implications of the bounds in practice.

Download activity - last month

Export as XMLJSONCSV

Download activity - last 12 months

Export as CSVJSONXML

Downloads by country - last 12 months

Export as CSVJSONXML

Archive Staff Only

View Item