论文标题
监督学习的无午餐定理
The no-free-lunch theorems of supervised learning
论文作者
论文摘要
无需午餐定理提出了一个怀疑的结论，即所有可能的机器学习算法同样缺乏理由。但是，这个学习理论的空间如何表明某些算法比其他算法更好？我们指出，与归纳哲学的绘制相似之处，无午餐的结果以纯粹的数据驱动为前提是学习算法的概念。在这个概念上，每种算法都必须具有固有的归纳偏见，需要理由。我们认为，许多标准学习算法应该被理解为模型依赖性：在每个应用程序中，它们还需要输入模型，代表偏差。通用算法本身，可以为它们提供模型相关的理由。
The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification. But how could this leave room for a learning theory, that shows that some algorithms are better than others? Drawing parallels to the philosophy of induction, we point out that the no-free-lunch results presuppose a conception of learning algorithms as purely data-driven. On this conception, every algorithm must have an inherent inductive bias, that wants justification. We argue that many standard learning algorithms should rather be understood as model-dependent: in each application they also require for input a model, representing a bias. Generic algorithms themselves, they can be given a model-relative justification.
