Publications de Luca Furieri | EPFL Graph Search

Parametrizations of all stable closed-loop responses: From theory to neural network control design

Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti

The complexity of modern control systems necessitates architectures that achieve high performance while ensuring robust stability, particularly for nonlinear systems. In this work, we tackle the challenge of designing output-feedback controllers to boost t ...

2025

Erratum to “Learning to Boost the Performance of Stable Nonlinear Systems”

Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti

Institute of Electrical and Electronics Engineers (IEEE)2025

On the Guarantees of Minimizing Regret in Receding Horizon

Giancarlo Ferrari Trecate, Luca Furieri, Andrea Martin

Toward bridging classical optimal control and online learning, regret minimization has recently been proposed as a control design criterion. This competitive paradigm penalizes the loss relative to the optimal control actions chosen by a clairvoyant policy ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2025

Learning to Boost the Performance of Stable Nonlinear Systems

Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti

The growing scale and complexity of safety-critical control systems underscore the need to evolve current control architectures aiming for the unparalleled performances achievable through state-of-the-art optimization and machine learning algorithms. Howev ...

2024

Learning to Optimize with Convergence Guarantees Using Nonlinear System Theory

Luca Furieri, Andrea Martin

The increasing reliance on numerical methods for controlling dynamical systems and training machine learning models underscores the need to devise algorithms that dependably and efficiently navigate complex optimization landscapes. Classical gradient desce ...

2024

Optimal distributed control with stability guarantees by training a network of neural closed-loop maps

Giancarlo Ferrari Trecate, Luca Furieri, Danilo Saccani, Leonardo Massai

This paper proposes a novel approach to improve the performance of distributed nonlinear control systems while preserving stability by leveraging Deep Neural Networks (DNNs). We build upon the Neural System Level Synthesis (Neur-SLS) framework and introduc ...

Institute of Electrical and Electronics Engineers Inc.2024

Closing the Gap to Quadratic Invariance: A Regret Minimization Approach to Optimal Distributed Control

Giancarlo Ferrari Trecate, Luca Furieri, Daniele Martinelli

In this work, we focus on the design of optimal controllers that must comply with an information structure. State-of-the-art approaches do so based on the H2 or H∞ norm to minimize the expected or worst-case cost in the presence of stochastic or adversaria ...

IEEE2024

Unconstrained Learning of Networked Nonlinear Systems via Free Parametrization of Stable Interconnected Operators

Giancarlo Ferrari Trecate, Luca Furieri, Danilo Saccani, Leonardo Massai

This paper characterizes a new parametrization of nonlinear networked incrementally L2 -bounded operators in discrete time. The distinctive novelty is that our parametrization is free - that is, a sparse large-scale operator with bounded incremental L2 gai ...

Institute of Electrical and Electronics Engineers Inc.2024

Regret optimal control for uncertain stochastic systems

Giancarlo Ferrari Trecate, Luca Furieri, Andrea Martin

We consider control of uncertain linear time-varying stochastic systems from the perspective of regret minimization. Specifically, we focus on the problem of designing a feedback controller that minimizes the loss relative to a clairvoyant optimal policy t ...

ELSEVIER2024

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 ...

2023