Search Results for author:
Found 14 papers, 10 papers with code
Learning to optimize with convergence guarantees using nonlinear system theory
The emerging paradigm of learning to optimize (L2O) automates the discovery of algorithms with optimized performance leveraging learning models and data - yet, it lacks a theoretical framework to analyze convergence and robustness of the learned algorithms.
Unconstrained learning of networked nonlinear systems via free parametrization of stable interconnected operators
Further, we can embed prior knowledge about the interconnection topology and stability properties of the system directly into the large-scale distributed operator we design.
Closing the Gap to Quadratic Invariance: a Regret Minimization Approach to Optimal Distributed Control
In this work, we focus on the design of optimal controllers that must comply with an information structure.
On the Guarantees of Minimizing Regret in Receding Horizon
Towards bridging classical optimal control and online learning, regret minimization has recently been proposed as a control design criterion.
Regret Optimal Control for Uncertain Stochastic Systems
Specifically, we focus on the problem of designing a feedback controller that minimizes the loss relative to a clairvoyant optimal policy that has foreknowledge of both the system dynamics and the exogenous disturbances.
Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations
We validate the properties of NodeRENs, including the possibility of handling irregularly sampled data, in a case study in nonlinear system identification.
Follow the Clairvoyant: an Imitation Learning Approach to Optimal Control
We consider control of dynamical systems through the lens of competitive analysis.
Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systems
We address the problem of designing stabilizing control policies for nonlinear systems in discrete-time, while minimizing an arbitrary cost function.
Safe Control with Minimal Regret
As we move towards safety-critical cyber-physical systems that operate in non-stationary and uncertain environments, it becomes crucial to close the gap between classical optimal control algorithms and adaptive learning-based methods.
Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach
A main challenge of NN controllers is that they are not dependable during and after training, that is, the closed-loop system may be unstable, and the training may fail due to vanishing and exploding gradients.
Non Vanishing Gradients for Arbitrarily Deep Neural Networks: a Hamiltonian System Approach
Deep Neural Networks (DNNs) training can be difficult due to vanishing or exploding gradients during weight optimization through backpropagation.
Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Design
Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation.
Near-Optimal Design of Safe Output Feedback Controllers from Noisy Data
As we transition towards the deployment of data-driven controllers for black-box cyberphysical systems, complying with hard safety constraints becomes a primary concern.
A Behavioral Input-Output Parametrization of Control Policies with Suboptimality Guarantees
Recent work in data-driven control has revived behavioral theory to perform a variety of complex control tasks, by directly plugging libraries of past input-output trajectories into optimal control problems.
