Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Bonnet, Benoit"'
Autor:
Bonnet, Benoît, Frankowska, Hélène
In this article, we prove a general viability theorem for continuity inclusions in Wasserstein spaces, and provide an application thereof to the existence of exponentially stable trajectories obtained via the second method of Lyapunov.
Externí odkaz:
http://arxiv.org/abs/2209.03640
Autor:
Bonalli, Riccardo, Bonnet, Benoît
In this paper, we derive first-order Pontryagin optimality conditions for risk-averse stochastic optimal control problems subject to final time inequality constraints, and whose costs are general, possibly non-smooth finite coherent risk measures. Un
Externí odkaz:
http://arxiv.org/abs/2204.03036
Publikováno v:
Mathematical Models and Methods in Applied SciencesVol. 32, No. 11, pp. 2121-2188 (2022)
In this article, we investigate the asymptotic formation of consensus for several classes of time-dependent cooperative graphon dynamics. After motivating the use of this type of macroscopic models to describe multi-agent systems, we adapt the classi
Externí odkaz:
http://arxiv.org/abs/2111.03900
Autor:
Bonnet, Benoît, Frankowska, Hélène
Publikováno v:
Journal de Math\'ematiques Pures et Appliqu\'eees, Published online (2021)
In this article, we investigate some of the fine properties of the value function associated to an optimal control problem in the Wasserstein space of probability measures. Building on new interpolation and linearisation formulas for non-local flows,
Externí odkaz:
http://arxiv.org/abs/2108.02609
Autor:
Bonnet, Benoît, Frankowska, Hélène
In this paper, we obtain several structural results for the value function associated to a mean-field optimal control problem of Bolza type in the space of measures. After establishing the sensitivity relations bridging between the costates of the ma
Externí odkaz:
http://arxiv.org/abs/2107.13912
In this paper we consider a measure-theoretical formulation of the training of NeurODEs in the form of a mean-field optimal control with $L^2$-regularization of the control. We derive first order optimality conditions for the NeurODE training problem
Externí odkaz:
http://arxiv.org/abs/2107.08707
Autor:
Bonnet, Benoît, Rossi, Francesco
We study a family of optimal control problems in which one aims at minimizing a cost that mixes a quadratic control penalization and the variance of the system, both for finitely many agents and for the mean-field dynamics as their number goes to inf
Externí odkaz:
http://arxiv.org/abs/2105.01158
Many defenses have emerged with the development of adversarial attacks. Models must be objectively evaluated accordingly. This paper systematically tackles this concern by proposing a new parameter-free benchmark we coin RoBIC. RoBIC fairly evaluates
Externí odkaz:
http://arxiv.org/abs/2102.05368
Autor:
Bonnet, Benoît, Frankowska, Hélène
In this article, we derive first-order necessary optimality conditions for a constrained optimal control problem formulated in the Wasserstein space of probability measures. To this end, we introduce a new notion of localised metric subdifferential f
Externí odkaz:
http://arxiv.org/abs/2101.10668
This paper explores the connection between steganography and adversarial images. On the one hand, ste-ganalysis helps in detecting adversarial perturbations. On the other hand, steganography helps in forging adversarial perturbations that are not onl
Externí odkaz:
http://arxiv.org/abs/2010.07542