Gradient methods for solving Stackelberg games

DOI10.1007/978-3-030-31489-7_9MaRDI QIDQ2290375zbMATH OpenOpenAlexFDO

Authors Roi Naveiro, David Ríos Insua

Publication date 27 January 2020

Full work available at URL https://arxiv.org/abs/1908.06901

zbMATH Keywords

adjoint methodadversarial machine learningautomatic differentiationgame theory

Mathematics Subject Classification ID

Hierarchical games (including Stackelberg games) (91A65) Algorithmic game theory and complexity (91A68)

Abstract: 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.

Recommendations

• Gradient methods for solving zero-sum linear-quadratic differential games
• scientific article; zbMATH DE number 165423
• scientific article; zbMATH DE number 6172813
• scientific article; zbMATH DE number 1931819
• scientific article; zbMATH DE number 4068657
• scientific article; zbMATH DE number 1193034
• Solution of n-person games by means of gradient method of prognostic type.
• Regularization and approximation methods in Stackelberg games and bilevel optimization
• Computing Stackelberg equilibria of large general-sum games

Cites work

• Adversarial classification: an adversarial risk analysis approach
• Adversarial risk analysis
• Convergence rate of \(\mathcal{O}(1/k)\) for optimistic gradient and extragradient methods in smooth convex-concave saddle point problems
• Derivative evaluation and computational experience with large bilevel mathematical programs
• Estimating classification error rate: repeated cross-validation, repeated hold-out and bootstrap
• Evaluating Derivatives
• scientific article; zbMATH DE number 53256 (Why is no real title available?)
• scientific article; zbMATH DE number 1569102 (Why is no real title available?)
• Optimization with PDE Constraints
• Security and Game Theory
• Some properties of the bilevel programming problem
• The elements of statistical learning. Data mining, inference, and prediction
• The polynomial hierarchy and a simple model for competitive analysis

Cited in

(7)

• Achieving optimal adversarial accuracy for adversarial deep learning using Stackelberg games
• Augmented probability simulation methods for sequential games
• scientific article; zbMATH DE number 7110187 (Why is no real title available?)
• Adversarial Machine Learning: Bayesian Perspectives
• A review of attacker-defender games: current state and paths forward
• Adversarial risk analysis: an overview
• Fifty years of reliability in operations research

This page was built for publication: Gradient methods for solving Stackelberg games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2290375)