ملف الباحث
Badr-Eddine Chérief-Abdellatif
ورقتان في مجموعة PaperMetrix
المنشورات
أوراق هذا المؤلف
-
Convergence Rates of Variational Inference in Sparse Deep Learning
2019 · arXiv (Cornell University)
Variational inference is becoming more and more popular for approximating intractable posterior distributions in Bayesian statistics and machine learning. Meanwhile, a few recent works have provided theoretical justification and new insights on deep neural networks …
-
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 $n$ …