3 citations · 5 across the 18 of their papers we have counts for
20 papers
Data-driven Koopman mode approximation: A neural power iteration algorithm
Guillaume O. Berger, Raphaël M. Jungers
This paper proposes a novel data-driven algorithm to approximate the dominant eigenfunctions (aka.~modes) of the Koopman operator of nonlinear dynamical systems using neural networ…
Direct vs. Indirect Data-Driven Control: Case-study of Switching Systems Stability
Alexis Vuille, Guillaume O. Berger, Raphaël M. Jungers
A central methodological question in data-driven control is whether to adopt a direct or indirect approach. Direct methods infer a controller or certificate directly from data, whi…
Robust Optimal Control of Arbitrarily Switched Systems: A Path-Complete Framework
Léa Ninite, Adrien Banse, Guillaume O. Berger +1
This paper addresses the robust control of switched systems under arbitrary switching with performance guarantees. We propose a framework that jointly synthesizes a feedback policy…
A Path-Complete Approach for Optimal Control of Switched Systems
Léa Ninite, Adrien Banse, Guillaume O. Berger +1
We study the problem of estimating the value function of discrete-time switched systems under arbitrary switching. Unlike the switched LQR problem, where both inputs and mode seque…
On the differentiability of the value function of switched linear systems under arbitrary and controlled switching
Guillaume O. Berger
This paper studies the differentiability of the value function of switched linear systems under arbitrary switching and controlled switching, referred to as worst-case and optimal…
Online Complexity Estimation for Repetitive Scenario Design
Guillaume O. Berger, Raphaël M. Jungers
We consider the problem of repetitive scenario design where one has to solve repeatedly a scenario design problem and can adjust the sample size (number of scenarios) to obtain a d…
A Stochastic-Optimization-Based Adaptive-Sampling Scheme for Data-Driven Stability Analysis of Switched Linear Systems
Alexis Vuille, Guillaume O. Berger, Raphaël M. Jungers
We introduce a novel approach based on stochastic optimization to find the optimal sampling distribution for the data-driven stability analysis of switched linear systems. Our goal…
Improved Compression Bounds for Scenario Decision Making
Guillaume O. Berger
Scenario decision making offers a flexible way of making decision in an uncertain environment while obtaining probabilistic guarantees on the risk of failure of the decision. The i…
Template-Based Piecewise Affine Regression
Guillaume O. Berger, Sriram Sankaranarayanan
We investigate the problem of fitting piecewise affine functions (PWA) to data. Our algorithm divides the input domain into finitely many polyhedral regions whose shapes are specif…
Data-driven invariant subspace identification for black-box switched linear systems
Guillaume O. Berger, Raphaël M. Jungers, Zheming Wang
We present an algorithmic framework for the identification of candidate invariant subspaces for switched linear systems. Namely, the framework allows to compute an orthonormal basi…
Counterexample-guided computation of polyhedral Lyapunov functions for hybrid systems
Guillaume O. Berger, Sriram Sankaranarayanan
This paper presents a counterexample-guided iterative algorithm to compute convex, piecewise linear (polyhedral) Lyapunov functions for uncertain continuous-time linear hybrid syst…
Learning fixed-complexity polyhedral Lyapunov functions from counterexamples
Guillaume O. Berger, Sriram Sankaranarayanan
We study the problem of synthesizing polyhedral Lyapunov functions for hybrid linear systems. Such functions are defined as convex piecewise linear functions, with a finite number…
Complexity of the LTI system trajectory boundedness problem
Guillaume O. Berger, Raphaël M. Jungers
We study the algorithmic complexity of the problem of deciding whether a Linear Time Invariant dynamical system with rational coefficients has bounded trajectories. Despite its ubi…
Bounds on set exit times of affine systems, using Linear Matrix Inequalities
Guillaume O. Berger, Maben Rabi
Efficient computation of trajectories of switched affine systems becomes possible, if for any such hybrid system, we can manage to efficiently compute the sequence of switching tim…
Data-driven control of switched linear systems with probabilistic stability guarantees
Zheming Wang, Guillaume O. Berger, Raphaël M. Jungers
This paper tackles state feedback control of switched linear systems under arbitrary switching. We propose a data-driven control framework that allows to compute a stabilizing stat…
Chance-constrained quasi-convex optimization with application to data-driven switched systems control
Guillaume O. Berger, Raphaël M. Jungers, Zheming Wang
We study quasi-convex optimization problems, where only a subset of the constraints can be sampled, and yet one would like a probabilistic guarantee on the obtained solution with r…
Finite Data-Rate Feedback Stabilization of Continuous-Time Switched Linear Systems with Unknown Switching Signal
Guillaume O. Berger, Raphaël M. Jungers
In this paper, we study the problem of stabilizing switched linear systems when only limited information about the state and the mode of the system is available, which occurs in ma…
On the Quality of First-Order Approximation of Functions with Hölder Continuous Gradient
Guillaume O. Berger, P. -A. Absil, Raphaël M. Jungers +1
We show that Hölder continuity of the gradient is not only a sufficient condition, but also a necessary condition for the existence of a global upper bound on the error of the firs…
Equivalent Polyadic Decompositions of Matrix Multiplication Tensors
Guillaume O. Berger, P. -A. Absil, Lieven De Lathauwer +2
Invariance transformations of polyadic decompositions of matrix multiplication tensors define an equivalence relation on the set of such decompositions. In this paper, we present a…
Path-complete -dominant switching linear systems
Guillaume O. Berger, Fulvio Forni, Raphaël M. Jungers
The notion of path-complete -dominance for switching linear systems (in short, path-dominance) is introduced as a way to generalize the notion of dominant/slow modes for LTI sys…