Abstract | ||
---|---|---|
We study regression problems in which an adversary can exercise some control over the data generation process. Learner and adversary have conflicting but not necessarily perfectly antagonistic objectives. We study the case in which the learner is not fully informed about the adversary’s objective; instead, any knowledge of the learner about parameters of the adversary’s goal may be reflected in a Bayesian prior. We model this problem as a Bayesian game, and characterize conditions under which a unique Bayesian equilibrium point exists. We experimentally compare the Bayesian equilibrium strategy to the Nash equilibrium strategy, the minimax strategy, and regular linear regression. |
Year | Venue | Field |
---|---|---|
2013 | ICML | Minimax,Computer science,Adversary model,Equilibrium point,Artificial intelligence,Adversary,Bayesian game,Nash equilibrium,Prior probability,Machine learning,Bayesian probability |
DocType | Citations | PageRank |
Conference | 11 | 0.76 |
References | Authors | |
10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Großhans | 1 | 11 | 0.76 |
Christoph Sawade | 2 | 55 | 6.21 |
Brückner, Michael | 3 | 397 | 19.82 |
Tobias Scheffer | 4 | 1862 | 139.64 |