3 papers
cs.GT2021
Scalable Optimal Classifiers for Adversarial Settings under Uncertainty
Patrick Loiseau, Benjamin Roussillon
We consider the problem of finding optimal classifiers in an adversarial setting where the class-1 data is generated by an attacker whose objective is not known to the defender --…
cs.GT2021
Asymptotic Degradation of Linear Regression Estimates With Strategic Data Sources
Benjamin Roussillon, Nicolas Gast, Patrick Loiseau +1
We consider the problem of linear regression from strategic data sources with a public good component, i.e., when data is provided by strategic agents who seek to minimize an indiv…
cs.GT2013
Linear Regression from Strategic Data Sources
Nicolas Gast, Stratis Ioannidis, Patrick Loiseau +1
Linear regression is a fundamental building block of statistical data analysis. It amounts to estimating the parameters of a linear model that maps input features to corresponding…