DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication
Contribución de congreso (ConferenceOutput)
Gradient methods for solving Stackelberg games
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, intervening 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 generally 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., R. Naveiro acknowledges the Spanish Ministry for his grant FPU15-03636. The work of D.R. Insua is supported by the Spanish Ministry program MTM2017-86875-C3-1-R and the AXA-ICMAT Chair on Adversarial Risk Analysis. D.R. Insua also acknowledges the support of the EU’s Horizon 2020 project 815003-2 TRUSTONOMY and the RTC-2017-6593-7 project., Peer reviewed
Project:
MECD / Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 FPU2015-03636
,
AEI MTM2017-86875-C3-1-R
DOI: http://hdl.handle.net/10261/346586, https://api.elsevier.com/content/abstract/scopus_id/85075630330
HANDLE: http://hdl.handle.net/10261/346586, https://api.elsevier.com/content/abstract/scopus_id/85075630330