arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.09159stat.MLcs.LG
收藏

基于黑盒估计器的贝叶斯量化

Bayesian Quantification with Black-Box Estimators

ETH AI Center and Department of Biosystems Science and Engineering, ETH Zürich(苏黎世联邦理工学院人工智能中心及生物系统科学与工程系)

Albert Ziegler, Paweł Czyż

AI总结:

针对无标签数据类别分布估计问题,提出一种关联现有黑盒估计器的贝叶斯模型,设计高效MCMC采样方案并证明渐近一致性,实验显示其性能具竞争力且部分场景更优。

摘要:

了解无标签数据集中不同类别的分布情况,是概率分类器校准与不确定性量化领域的一项重要挑战。调整后分类计数法、黑盒偏移估计器、不变比率估计器等方法,均借助在不同(存在分布偏移)数据集上训练的辅助(且可能存在偏差)黑盒分类器来估计类别分布,并在弱假设下具备渐近保证。我们证明,所有这些算法都与某一特定贝叶斯模型的推断过程密切相关,该模型近似于假设的真实生成过程。随后,我们针对所提出的模型设计了一种高效的马尔可夫链蒙特卡洛采样方案,并证明其在大数据极限下具备渐近一致性保证。我们在多种场景下将该模型与已有的点估计器进行对比,结果表明其性能具有竞争力,在部分场景下优于现有最优方法。

英文摘要:

Understanding how different classes are distributed in an unlabeled data set is an important challenge for the calibration of probabilistic classifiers and uncertainty quantification. Approaches like adjusted classify and count, black-box shift estimators, and invariant ratio estimators use an auxiliary (and potentially biased) black-box classifier trained on a different (shifted) data set to estimate the class distribution and yield asymptotic guarantees under weak assumptions. We demonstrate that all these algorithms are closely related to the inference in a particular Bayesian model, approximating the assumed ground-truth generative process. Then, we discuss an efficient Markov Chain Monte Carlo sampling scheme for the introduced model and show an asymptotic consistency guarantee in the large-data limit. We compare the introduced model against the established point estimators in a variety of scenarios, and show it is competitive, and in some cases superior, with the state of the art.

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。

↑