2019

Safe-Bayesian Generalized Linear Regression

de Heide, Rianne, Kirichenko, Alisa, Mehta, Nishant et al.

Understand

We study generalized Bayesian inference under misspecification, i.e.

  • when the model is 'wrong but useful'.
  • Generalized Bayes equips the likelihood with a learning rate $\eta$.
  • We show that for generalized linear models (GLMs), $\eta$-generalized Bayes concentrates around the best approximation of the truth within the model for specific $\eta \neq 1$, even under severely misspecified noise, as long as the tails of the true distribution are exponential.

Reading the bibliography…