Generalization error for Tweedie models: decomposition and error reduction with bagging

Wüthrich and Buser (DOI:10.2139/ssrn.2870308, 2020) studied the generalization error for Poisson regression models. This short note aims to extend their results Tweedie family of distributions, which law belongs. In case bagging, a new condition emerges that becomes increasingly binding with power parameter involved in variance function.