Robust and Adaptive Functional Logistic Regression

We introduce and study a family of robust estimators for the functional logistic regression model whose robustness automatically adapts to the data thereby leading to estimators with high efficiency in clean data and a high degree of resistance towards atypical observations. The estimators are based on the concept of density power divergence between densities and may be formed with any combination of lower rank approximations and penalties, as the need arises. For these estimators we prove uniform convergence and high rates of convergence with respect to the commonly used prediction error under fairly general assumptions. The highly competitive practical performance of our proposal is illustrated on a simulation study and a real data example which includes atypical observations.