关于二元分类器的Kolmogorov复杂度
On the Kolmogorov Complexity of Binary Classifiers
摘要:
我们提供了严格的上限和下限的预期最低柯尔莫哥洛夫复杂度的二进制分类器是一致的标记样本。期望的大小不超过目标概念的复杂度加上给定样本的标签的条件熵。
英文摘要:
We provide tight upper and lower bounds on the expected minimum Kolmogorov complexity of binary classifiers that are consistent with labeled samples. The expected size is not more than complexity of the target concept plus the conditional entropy of the labels given the sample.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。