arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.09381stat.ME
收藏

风险最小化的直接吉布斯后验推理:构造、集中和校准

Direct Gibbs posterior inference on risk minimizers: construction, concentration, and calibration

Ryan Martin, Nicholas Syring

摘要:

现实世界的问题,通常被描述为机器学习应用程序,涉及具有现实意义的感兴趣的量,独立于任何统计模型。为了避免潜在的模型误指定的偏见或过于复杂的问题制定,一个直接的,无模型的方法是必要的。传统的贝叶斯框架依赖于数据生成过程的模型,因此,显然,所需的直接,无模型,后验概率推理是遥不可及的。幸运的是,似然函数并不是连接数据和感兴趣的量的唯一方法。损失函数提供了另一种联系,其中利息的数量被定义为或至少可以被定义为相应风险或预期损失的最小化者。在这种情况下,人们可以通过直接使用经验风险函数来获得通常所称的吉布斯后验分布。本文探讨了吉布斯后验结构,它的渐近浓度特性,以及它的可信区域的频率校准。由于不受模型规范的约束,吉布斯后验为现代统计学习问题中的概率推理创造了新的机会。

英文摘要:

Real-world problems, often couched as machine learning applications, involve quantities of interest that have real-world meaning, independent of any statistical model. To avoid potential model misspecification bias or over-complicating the problem formulation, a direct, model-free approach is desired. The traditional Bayesian framework relies on a model for the data-generating process so, apparently, the desired direct, model-free, posterior-probabilistic inference is out of reach. Fortunately, likelihood functions are not the only means of linking data and quantities of interest. Loss functions provide an alternative link, where the quantity of interest is defined, or at least could be defined, as a minimizer of the corresponding risk, or expected loss. In this case, one can obtain what is commonly referred to as a Gibbs posterior distribution by using the empirical risk function directly. This manuscript explores the Gibbs posterior construction, its asymptotic concentration properties, and the frequentist calibration of its credible regions. By being free from the constraints of model specification, Gibbs posteriors create new opportunities for probabilistic inference in modern statistical learning problems.

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。

↑