Automatic Debiased Machine Learning via Neural Nets for Generalized Linear Regression
Generalized linear regressions are linear combinations of many regressors that set a residual orthogonal to the regressors. These include objects that are nonparametrically estimated in generalized linear models. We give debiased machine learners of parameters of interest that depend on generalized linear regressions. The parameters of interest include many causal and policy effects. We give neural net learners of the bias correction that are automatic in only depending on the object of interest and the regression residual. Convergence rates are given for these neural nets and for more general learners of the bias correction. We also give conditions for asymptotic normality and consistent asymptotic variance estimation of the learner of the object of interest.
LOCATION:Zoom - please contact emilie_campanelli@fas.harvard.edu for more information STATUS:CONFIRMED DTSTART:20211115T170000Z DTEND:20211115T180000Z END:VEVENT END:VCALENDAR