Learning from Survey Training Samples: Rate Bounds for Horvitz-Thompson Risk Minimizers

18 Jan 2019 Stephan Clémençon Bertail Patrice Papa Guillaume

The generalization ability of minimizers of the empirical risk in the context of binary classification has been investigated under a wide variety of complexity assumptions for the collection of classifiers over which optimization is performed. In contrast, the vast majority of the works dedicated to this issue stipulate that the training dataset used to compute the empirical risk functional is composed of i.i.d... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Categories


  • STATISTICS THEORY
  • STATISTICS THEORY