Charles Riou

Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes

2023 · HAL (Le Centre pour la Communication Scientifique Directe)

Bernstein's condition is a key assumption that guarantees fast rates in machine learning. For example, the Gibbs algorithm with prior $π$ has an excess risk in $O(d_π/n)$, as opposed to the standard $O(\sqrt{d_π/n})$, where $n$ …