1,724,002 research outputs found
Stochastic Generalized Nash Equilibrium-Seeking in Merely Monotone Games
Full text linkWe solve the stochastic generalized Nash equilibrium (SGNE) problem in merely monotone games with expected value cost functions. Specifically, we present the first distributed SGNE-seeking algorithm for monotone games that require one proximal computation (e.g., one projection step) and one pseudogradient evaluation per iteration. Our main contribution is to extend the relaxed forward–backward operator splitting by the Malitsky (Mathematical Programming, 2019) to the stochastic case and in turn to show almost sure convergence to an SGNE when the expected value of the pseudogradient is approximated by the average over a number of random samples.Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Team Sergio GrammaticoTeam Bart De Schutte
A distributed forward-backward algorithm for stochastic generalized Nash equilibrium seeking
No full textWe consider the stochastic generalized Nash equilibrium problem (SGNEP) with expected-value cost functions. Inspired by Yi and Pavel (2019), we propose a distributed generalized Nash equilibrium seeking algorithm based on the preconditioned forward-backward operator splitting for SGNEPs, where, at each iteration, the expected value of the pseudogradient is approximated via a number of random samples. Our main contribution is to show almost sure convergence of the proposed algorithm if the pseudogradient mapping is restricted (monotone and) cocoercive.Accepted Author ManuscriptTeam Bart De Schutte
Giuseppina Grammatico Amari
Full text linkObituario de la Profesora Giuseppina Grammatico Amar.Centro de Estudios de Lenguas Clásicas. Area Filología Grieg
Training Generative Adversarial Networks via Stochastic Nash Games
No full textGenerative adversarial networks (GANs) are a class of generative models with two antagonistic neural networks: a generator and a discriminator. These two neural networks compete against each other through an adversarial process that can be modeled as a stochastic Nash equilibrium problem. Since the associated training process is challenging, it is fundamental to design reliable algorithms to compute an equilibrium. In this article, we propose a stochastic relaxed forward-backward (SRFB) algorithm for GANs, and we show convergence to an exact solution when an increasing number of data is available. We also show convergence of an averaged variant of the SRFB algorithm to a neighborhood of the solution when only a few samples are available. In both cases, convergence is guaranteed when the pseudogradient mapping of the game is monotone. This assumption is among the weakest known in the literature. Moreover, we apply our algorithm to the image generation problem.</p
Corrigendum to “Stochastic generalized Nash equilibrium seeking under partial-decision information” [Automatica 137 (2022) 110101] (Automatica (2022) 137, (S0005109821006300), (10.1016/j.automatica.2021.110101))
No full textThe following paragraph was inadvertently omitted from the final version of the paper (Franci & Grammatico, 2022). The paragraph was to be placed at the end of the Introduction section: “Finally, let us remark that our setting, and in general, the literature on SGNEPs, assumes that the agents have access to stochastic (partial) first-order information, specifically, random samples of the pseudogradient, as opposed to zeroth-order information, i.e., direct measurements of the cost functions as in extremum seeking (Frihauf, Krstic, & Basar, 2011; Krilašević & Grammatico, 2021; Liu & Krstić, 2011). In particular, the SGNEP literature assumes that the random samples of first-order information are given, hence cannot be controlled, while the extremum-seeking literature assumes that the available zeroth-order information is deterministic and results from a controlled perturbation injected into the system”.Corrigendum DOI 10.1016/j.automatica.2021.110101Team Bart De SchutterTeam Sergio Grammatic
Guest Editorial: Introduction to IEEE Control Systems Letters Special Section on Multi-Agent Coordination for Energy Systems: From Model Based to Data-Driven Methods
Full text linkEditorialGreen Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Team Sergio GrammaticoTeam Bart De Schutte
Mosco di Siracusa, poeta e grammatico
No full textIl Mosco di Siracusa, secondo poeta bucolico della triade canonica, il Mosco grammatico citato da Athen. XI 484f, probabilmente il Mosco meccanico menzionato dallo stesso Athen. XIV 634b, e forse persino il Moschione citato in Athen. V 206d potrebbero essere la stessa persona: una figura di poeta-grammatico con interessi tecnico-scientifici del tutto consona all'età e alla cultura alessandrina
La biblioteca di un grammatico
No full textRicostruire la biblioteca di un grammatico non è sempre impresa agevole, specie se il grammatico in questione, Giuniano Maio, in sintonia con una temperie culturale che enfatizzava la lettura diretta degli auctores e tuonava contro la fallace erudizione di compilatori medievali, amava dissimulare la presenza nel suo scriptorium di materiali non proprio à la page, per non incorrere negli strali di qualche integralista della valliana eleganza.Pubblicato a Napoli nel 1475, il lessico De priscorum proprietate verborum fu edito altre cinque volte, ben tre a Venezia. Il volume di Palumbo ne ricostruisce le fonti, soffermandosi sul sospetto di plagio che grava sull’opera, ed esamina la fortuna della pregevole compilazione
Stochastic generalized Nash equilibrium seeking under partial-decision information
Full text linkWe consider for the first time a stochastic generalized Nash equilibrium problem, i.e., with expected-value cost functions and joint feasibility constraints, under partial-decision information, meaning that the agents communicate only with some trusted neighbors. We propose several distributed algorithms for network games and aggregative games that we show being special instances of a preconditioned forward–backward splitting method. We prove that the algorithms converge to a generalized Nash equilibrium when the forward operator is restricted cocoercive by using the stochastic approximation scheme with variance reduction to estimate the expected value of the pseudogradient.Team Sergio GrammaticoTeam Bart De Schutte
- …
