发表机构
Hasso Plattner Institute; University of Potsdam（哈索·普拉特纳研究院; 波茨坦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出统一视角，将概率视为预测方法的输出，论证其模型依赖性，并证明满足有限校准准则时可用于有效决策。
AI 中文摘要
尽管概率陈述无处不在，但关于其理解的基础性分歧依然存在，例如贝叶斯学派与频率学派之间的争论；此外，人们尚不清楚何时以及为何依据概率行事实际上会带来理想的结果。在此，我们论证每一个概率都是某种“预测方法”的输出，即它既依赖于构建抽象的一种特定方式，也依赖于将这些抽象转化为预测的方式。通过这一点，我们为表面上不同类型的概率提供了一个统一的视角，并表明即使是看似客观的概率也是依赖于模型的。我们证明，当满足一个有限的校准准则时，人们可以预期给定策略下效用的分布，并在有限事件集上支持成功的决策制定。基于预测方法的概念、归纳论证和概率演算，我们解释了校准准则在许多情境下的可行性。总体而言，我们发展了一个关于概率及其使用的连贯视角，并在此过程中连接了其他解释背后的关键直觉。
英文摘要
Although probabilistic statements are ubiquitous, foundational disagreements persist about their understanding, as exemplified by debates between Bayesians and frequentists; moreover, it is unclear when and why acting on them actually leads to desirable outcomes. Here, we argue that every probability is the output of a \emph{prediction method}, that is, it depends on both a particular way of constructing abstractions and a way of transforming them into predictions. Through this, we provide a unifying perspective on supposedly different kinds of probabilities and show that even supposedly objective ones are model-dependent. We demonstrate that when a finite calibration criterion is met, one can anticipate the distribution of utilities for a given policy and inform successful decision-making on finite sets of events. Based on the notion of prediction methods, inductive arguments, and the probability calculus, we explain the feasibility of the calibration criterion in many settings. Overall, we develop a coherent perspective on probabilities and their use, connecting key intuitions behind other interpretations along the way.
