Asymptotic Degradation of Linear Regression Estimates with Strategic Data Sources - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année :

Asymptotic Degradation of Linear Regression Estimates with Strategic Data Sources

(1) , (1) , (1, 2) , (1, 3)
1
2
3

Résumé

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 individual provision cost for increasing their data's precision while benefiting from the model's overall precision. In contrast to previous works, our model tackles the case where there is uncertainty on the attributes characterizing the agents' data -- a critical aspect of the problem when the number of agents is large. We provide a characterization of the game's equilibrium, which reveals an interesting connection with optimal design. Subsequently, we focus on the asymptotic behavior of the covariance of the linear regression parameters estimated via generalized least squares as the number of data sources becomes large. We provide upper and lower bounds for this covariance matrix and we show that, when the agents' provision costs are superlinear, the model's covariance converges to zero but at a slower rate relative to virtually all learning problems with exogenous data. On the other hand, if the agents' provision costs are linear, this covariance fails to converge. This shows that even the basic property of consistency of generalized least squares estimators is compromised when the data sources are strategic.

Dates et versions

hal-03593516 , version 1 (02-03-2022)

Identifiants

Citer

Benjamin Roussillon, Nicolas Gast, Patrick Loiseau, Panayotis Mertikopoulos. Asymptotic Degradation of Linear Regression Estimates with Strategic Data Sources. ALT 2022 - 33rd International Conference on Algorithmic Learning Theory, Mar 2022, Paris, France. pp.1-31. ⟨hal-03593516⟩
49 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More