Person
Luca Furieri
Related publications (20)
Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design
Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti, Liang Xu
Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretiz ...
2023Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations
Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti, Daniele Martinelli
In this work, we introduce and study a class of Deep Neural Networks (DNNs) in continuous-time. The proposed architecture stems from the combination of Neural Ordinary Differential Equations (Neural ODEs) with the model structure of recently introduced Rec ...
New York2023Follow the Clairvoyant: an Imitation Learning Approach to Optimal Control
Giancarlo Ferrari Trecate, John Lygeros, Luca Furieri, Florian Dörfler, Andrea Martin
We consider control of dynamical systems through the lens of competitive analysis. Most prior work in this area focuses on minimizing regret, that is, the loss relative to an ideal clairvoyant policy that has noncausal access to past, present, and future d ...
Elsevier2023Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach
Giancarlo Ferrari Trecate, Luca Furieri, Muhammad Zakwan, Clara Lucía Galimberti
Large-scale cyber-physical systems require that control policies are distributed, that is, that they only rely on local real-time measurements and communication with neighboring agents. Optimal Distributed Control (ODC) problems are, however, highly intrac ...
2022Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systems
Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti
We address the problem of designing stabilizing control policies for nonlinear systems in discrete-time, while minimizing an arbitrary cost function. When the system is linear and the cost is convex, the System Level Synthesis (SLS) approach offers an effe ...
IEEE2022Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback Systems
Maryam Kamgarpour, Luca Furieri, Na Li
This paper studies a class of partially observed Linear Quadratic Gaussian (LQG) problems with unknown dynamics. We establish an end-to-end sample complexity bound on learning a robust LQG controller for open-loop stable plants. This is achieved using a ro ...
PMLR2021Learning Robustly Safe Output Feedback Controllers from Noisy Data with Performance Guarantees
Giancarlo Ferrari Trecate, Luca Furieri, Baiwei Guo, Andrea Martin
How can we synthesize a safe and near-optimal control policy for a partially-observed system, if all we are given is one historical input/output trajectory that has been corrupted by noise? To address this challenge, we suggest a novel data-driven controll ...
2021Optimal Linear Controller for Minimizing DC Voltage Oscillations in MMC-Based Offshore Multiterminal HVDC Grids
Maryam Kamgarpour, Luca Furieri
The paper aims at minimizing DC voltage oscillations in offshore multiterminal high-voltage direct current (HVDC) grids based on modular multilevel converters (MMCs). The DC voltage stability is a crucial factor in multiterminal HVDC networks since it is a ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021On the Equivalence of Youla, System-Level, and Input-Output Parameterizations
Maryam Kamgarpour, Luca Furieri, Yu Zheng
A convex parameterization of internally stabilizing controllers is fundamental for many controller synthesis procedures. The celebrated Youla parameterization relies on a doubly coprime factorization of the system, while the recent system-level and input-o ...
2021First Order Methods For Globally Optimal Distributed Controllers Beyond Quadratic Invariance
Maryam Kamgarpour, Luca Furieri
We study the distributed Linear Quadratic Gaussian (LQG) control problem in discrete-time and finite-horizon, where the controller depends linearly on the history of the outputs and it is required to lie in a given subspace, e.g. to possess a certain spars ...
IEEE2020