论文标题
关于$ f $ divergences的措施不平等的变更
On change of measure inequalities for $f$-divergences
论文作者
论文摘要
我们提出了基于$ f $ diverences（kullback-leibler Divergence是一种特殊情况）的新度量不平等现象的新更改。我们的策略依赖于结合$ f $ diverences和Young Fenchel不平等的Legendre转型。通过利用这些新的措施不平等的变化，我们得出了新的Pac-Bayesian泛化界限，其复杂性涉及$ f $ divergences，并在大多数未经许可的环境（例如重尾损失）中持有。我们将结果实例化最受欢迎的$ f $ didiverences。
We propose new change of measure inequalities based on $f$-divergences (of which the Kullback-Leibler divergence is a particular case). Our strategy relies on combining the Legendre transform of $f$-divergences and the Young-Fenchel inequality. By exploiting these new change of measure inequalities, we derive new PAC-Bayesian generalisation bounds with a complexity involving $f$-divergences, and holding in mostly unchartered settings (such as heavy-tailed losses). We instantiate our results for the most popular $f$-divergences.
