发表机构
Munich Center for Mathematical Philosophy (MCMP), LMU Munich; Munich Center for Machine Learning (MCML)（慕尼黑大学慕尼黑数学哲学中心（MCMP）; 慕尼黑机器学习中心（MCML））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文基于统计学习理论，从手段-目的角度论证了正则化程序的合理性，为奥卡姆剃刀原则提供了方法论层面的辩护，既非单纯实用原则也非本体论假设。
AI 中文摘要
奥卡姆剃刀原则要求在归纳推理中偏好简单性，在科学哲学和机器学习领域均受到大量关注，但两领域中对该原则的论证一直难以获得。本文基于早期的“核心论证”，从统计学习理论角度对正则化程序（即权衡拟合度与简单性）进行论证。该手段-目的论证指出，为获得理论可靠性及“所见即所得”保证，必须对简单性赋予一定程度的偏好，而非拟合度。这是一种真正的方法论论证，既不沦为单纯因偏好简单性自身的实用原则，也不沦为“真理是简单的”这种本体论假设。
英文摘要
The principle of Occam's razor, which instructs us to prefer simplicity in inductive inference, has attracted much scrutiny both in the philosophy of science and in machine learning. In either field, however, a justification for the principle has been elusive. In this paper, building on an earlier "core argument," I spell out a justification from statistical learning theory for the procedure of regularization: for trading off fit for simplicity. The means-ends argument is that in order to profit from theoretical reliability and "what-you-see-is-what-you-get" guarantees, one must implement a certain preference for simplicity over fit. This is a genuine methodological justification, which neither collapses to a purely pragmatic principle that we prefer simplicity for its own sake, nor to an ontological assumption that the truth is simple.
