论文标题
通过并发验证者对学习的概括分析
Generalization Analysis on Learning with a Concurrent Verifier
论文作者
论文摘要
机器学习技术已在各种实用系统中使用。在实际情况下，自然可以期望机器学习模型的投入输出对满足某些要求。但是，很难通过仅从示例中学习来满足要求的模型。一个简单的解决方案是添加一个模块，该模块检查输入输出对是否满足要求，然后修改模型的输出。我们称之为{\ em并发验证者}（CV）的模块可以给出认证，尽管使用CV的机器学习模型的概括性如何更改尚不清楚。本文通过简历对学习进行了概括分析。我们分析了机器学习模型的可学习性如何随着简历而变化，并显示了只有在推理时间内使用验证者获得保证的假设的条件。我们还表明，在多级分类和结构化预测设置中使用CV时，基于Rademacher复杂性的典型误差界限将比原始模型的界限大。
Machine learning technologies have been used in a wide range of practical systems. In practical situations, it is natural to expect the input-output pairs of a machine learning model to satisfy some requirements. However, it is difficult to obtain a model that satisfies requirements by just learning from examples. A simple solution is to add a module that checks whether the input-output pairs meet the requirements and then modifies the model's outputs. Such a module, which we call a {\em concurrent verifier} (CV), can give a certification, although how the generalizability of the machine learning model changes using a CV is unclear. This paper gives a generalization analysis of learning with a CV. We analyze how the learnability of a machine learning model changes with a CV and show a condition where we can obtain a guaranteed hypothesis using a verifier only in the inference time. We also show that typical error bounds based on Rademacher complexity will be no larger than that of the original model when using a CV in multi-class classification and structured prediction settings.
