28 citations · 30 across the 13 of their papers we have counts for
3 papers · 1 filter
Properties of Immersions for Systems with Multiple Limit Sets with Implications to Learning Koopman Embeddings
Zexiang Liu, Necmiye Ozay, Eduardo D. Sontag
Linear immersions (such as Koopman eigenfunctions) of a nonlinear system have wide applications in prediction and control. In this work, we study the properties of linear immersion…
Small-Disturbance Input-to-State Stability of Perturbed Gradient Flows: Applications to LQR Problem
Leilei Cui, Zhong-Ping Jiang, Eduardo D. Sontag
This paper studies the effect of perturbations on the gradient flow of a general nonlinear programming problem, where the perturbation may arise from inaccurate gradient estimation…
Why should autoencoders work?
Matthew D. Kvalheim, Eduardo D. Sontag
Deep neural network autoencoders are routinely used computationally for model reduction. They allow recognizing the intrinsic dimension of data that lie in a -dimensional subset…