Lean Formalization of Generalization Error Bound by Rademacher Complexity and Dudley's Entropy Integral 事件

Lean Formalization of Generalization Error Bound by Rademacher Complexity and Dudley's Entropy Integral arXiv:2503.19605v5 Announce Type: replace-cross Abstract: Understanding and certifying the generalization performance of machine learning algorithms -- i.e. obtaining theoretical estimates of the test error from the training error -- is a central theme of statistical learning theory. Among the many complexity measures used to derive such guarantees, Rademacher complexity yields sharp, data-de