个体数据的通用监督学习
Universal Supervised Learning for Individual Data
摘要：
通用监督学习是从信息理论的角度考虑的，遵循通用预测方法，参见Merhav和Feder（1998）。我们考虑标准的监督“批”学习，其中一旦观察到整个训练数据，就对测试样本进行预测，以及单独设置，其中训练和测试中的特征和标签都是特定的个体量。信息论方法自然使用自信息损失或对数损失。我们的研究结果提供了通用的学习方案，与“精灵”（或参考），知道真正的测试标签竞争。特别是，它表明，主要提出的计划，称为预测归一化最大似然（pNML），是一个强大的学习解决方案，优于目前领先的方法的基础上经验风险最小化（ERM）。此外，pNML构造提供了针对特定测试挑战的可学习性的逐点指示，该特定测试挑战具有给定的训练样本
英文摘要：
Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where prediction is done on a test sample once the entire training data is observed, and the individual setting where the features and labels, both in the training and test, are specific individual quantities. The information theoretic approach naturally uses the self-information loss or log-loss. Our results provide universal learning schemes that compete with a "genie" (or reference) that knows the true test label. In particular, it is demonstrated that the main proposed scheme, termed Predictive Normalized Maximum Likelihood (pNML), is a robust learning solution that outperforms the current leading approach based on Empirical Risk Minimization (ERM). Furthermore, the pNML construction provides a pointwise indication for the learnability of the specific test challenge with the given training examples
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。
