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.
Gradient Methods for Solving Stackelberg Games
2019-10-23
oai:zenodo.org:4543484
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC: | 629 |
Stackelberg games and multiple equilibrium behaviors on networks
Elsevier | 2007
|Stackelberg games and multiple equilibrium behaviors on networks
Online Contents | 2007
|A New Global Optimization Method for Solving the Stackelberg Problem
British Library Online Contents | 1993
|