#optazur Learning Dynamical Systems Via Koopman Operator Regression

par Massimiliano Pontil (talian Institute of Technology and University College London)

lundi 20 nov. 2023, 14:00 → 15:00 Europe/Paris

salle de conférences (LJAD)

Non-linear dynamical systems can be handily described by the associated Koopman operator, whose action evolves every observable of the system forward in time. These operators are instrumental to forecasting and interpreting the system dynamics, and have broad applications in science and engineering. The talk gives a gentle introduction to this topic, with a focus on theory and algorithms. We highlight the importance of algorithms that allow us to estimate the spectral decomposition of the Koopman operator well and explore how the quest for good representations for these operators can be formulated as an optimization problem involving neural networks.