activity
20032023
most citedLinear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control

1.2k citations · 3.3k across the 35 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.LG2020★ 4 cited

Predicting the Critical Number of Layers for Hierarchical Support Vector Regression

Ryan Mohr, Maria Fonoberova, Zlatko Drmač +2

Hierarchical support vector regression (HSVR) models a function from data as a linear combination of SVR models at a range of scales, starting at a coarse scale and moving to finer…

math.DS2020★ 10 cited

Koopman Operator, Geometry, and Learning

Igor Mezic

We provide a framework for learning of dynamical systems rooted in the concept of representations and Koopman operators. The interplay between the two leads to the full description…

math.DS2020

On Numerical Approximations of the Koopman Operator

Igor Mezic

We study numerical approaches to computation of spectral properties of composition operators. We provide a characterization of Koopman Modes in Banach spaces using Generalized Lapl…

math.DS2020

Koopman Resolvent: A Laplace-Domain Analysis of Nonlinear Autonomous Dynamical Systems

Yoshihiko Susuki, Alexandre Mauroy, Igor Mezic

The motivation of our research is to establish a Laplace-domain theory that provides principles and methodology to analyze and synthesize systems with nonlinear dynamics. A semigro…

cs.LG2020★ 10 cited

Applications of Koopman Mode Analysis to Neural Networks

Iva Manojlović, Maria Fonoberova, Ryan Mohr +4

We consider the training process of a neural network as a dynamical system acting on the high-dimensional weight space. Each epoch is an application of the map induced by the optim…

nlin.PS2020★ 31 cited

Spectral Analysis of the Koopman Operator for Partial Differential Equations

Hiroya Nakao, Igor Mezić

We provide an overview of the Koopman operator analysis for a class of partial differential equations describing relaxation of the field variable to a stable stationary state. We i…