论文标题
关于在可实现的情况下，关于VC课程适当学习者的信息复杂性
On the Information Complexity of Proper Learners for VC Classes in the Realizable Case
论文作者
论文摘要
我们通过证明它们绑定在Vapnik-ChervoneNkis（VC）课程的有条件的相互信息（CMI）上，从而无法从$ d \ log n +2 $ o（$ o（d）$（$ o（d）$ n $ n $ n $ n $ i.i i.i i.i.d。培训例子。实际上，我们展示了VC类别，任何适当学习者的CMI不能仅受VC维度的任何实现功能的界限。
We provide a negative resolution to a conjecture of Steinke and Zakynthinou (2020a), by showing that their bound on the conditional mutual information (CMI) of proper learners of Vapnik--Chervonenkis (VC) classes cannot be improved from $d \log n +2$ to $O(d)$, where $n$ is the number of i.i.d. training examples. In fact, we exhibit VC classes for which the CMI of any proper learner cannot be bounded by any real-valued function of the VC dimension only.
