Publications (6)
Diffeomorphically Learning Stable Koopman Operators
Petar Bevanda, Max Beier, Sebastian Kerz +3
System representations inspired by the infinite-dimensional Koopman operator (generator) are increasingly considered for predictive modeling. Due to the operator's linearity, a ran…
Towards Data-driven LQR with Koopmanizing Flows
Petar Bevanda, Max Beier, Shahab Heshmati-Alamdari +2
We propose a novel framework for learning linear time-invariant (LTI) models for a class of continuous-time non-autonomous nonlinear dynamics based on a representation of Koopman o…
Koopman-Equivariant Gaussian Processes
Petar Bevanda, Max Beier, Armin Lederer +3
Credible forecasting and representation learning of dynamical systems are of ever-increasing importance for reliable decision-making. To that end, we propose a family of Gaussian p…
Koopman Kernel Regression
Petar Bevanda, Max Beier, Armin Lederer +3
Many machine learning approaches for decision making, such as reinforcement learning, rely on simulators or predictive models to forecast the time-evolution of quantities of intere…
Operator Models for Continuous-Time Offline Reinforcement Learning
Nicolas Hoischen, Petar Bevanda, Max Beier +3
Continuous-time stochastic processes underlie many natural and engineered systems. In healthcare, autonomous driving, and industrial control, direct interaction with the environmen…
Sequence Modeling with Spectral Mean Flows
Jinwoo Kim, Max Beier, Petar Bevanda +2
A key question in sequence modeling with neural networks is how to represent and learn highly nonlinear and probabilistic state dynamics. Operator theory views such dynamics as lin…