Stackelberg Games are gaining importance in the last years due to the raise of Adversarial Machine Learning (AML). Within this context, a new paradigm must be faced: in classical game theory, inter- vening agents were humans whose decisions are generally discrete and low dimensional. In AML, decisions are made by algorithms and are usually continuous and high dimensional, e.g. choosing the weights of a neural network. As closed form solutions for Stackelberg games gener- ally do not exist, it is mandatory to have efficient algorithms to search for numerical solutions. We study two different procedures for solving this type of games using gradient methods. We study time and space scalability of both approaches and discuss in which situation it is more appropriate to use each of them. Finally, we illustrate their use in an adversarial prediction problem.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Gradient Methods for Solving Stackelberg Games


    Beteiligte:
    Roi Naveiro (Autor:in) / David Rios Insua (Autor:in)

    Erscheinungsdatum :

    2019-10-23


    Anmerkungen:

    oai:zenodo.org:4543484



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    Stackelberg games and multiple equilibrium behaviors on networks

    Yang, Hai / Zhang, Xiaoning / Meng, Qiang | Elsevier | 2007



    Dynamic Congestion Pricing Model Based on Stackelberg Games

    Ding, Lili / Wang, Zhengwei / Li, Luyan | ASCE | 2013


    Fragility and Robustness in Mean-Payoff Adversarial Stackelberg Games

    Balachander, Mrudula / Guha, Shibashis | BASE | 2021

    Freier Zugriff

    A New Global Optimization Method for Solving the Stackelberg Problem

    Shimizu, K. / Lu, M. | British Library Online Contents | 1993