May, 2024
递归 PAC-Bayes:一种在没有信息损失的情况下对顺序先验进行频率论更新的方法
Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
Yi-Shan Wu, Yijie Zhang, Badr-Eddine Chérief-Abdellatif, Yevgeny Seldin
TL;DRPAC-Bayesian analysis allows sequential prior updates with no information loss and has significant improvements in empirical evaluation.