arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.12090stat.MLcs.LG
收藏

领域专家参与的近似贝叶斯计算

Approximate Bayesian Computation with Domain Expert in the Loop

Aalto University(阿尔托大学);University of Manchester(曼彻斯特大学)

Ayush Bharti, Louis Filstroff, Samuel Kaski

摘要:

近似贝叶斯计算(ABC)是一种流行的似然自由推理方法,适用于具有复杂似然函数的模型。由于ABC方法通常依赖于比较观察数据和模拟数据的汇总统计量,因此统计量的选择至关重要。这种选择涉及信息损失和降维之间的权衡,并且通常基于领域知识来确定。然而,手工制作和选择合适的统计数据是一项艰巨的任务,涉及多个试错步骤。在这项工作中,我们引入了一种主动学习方法ABC统计选择,大大减少了领域专家的工作。与现有的降维方法不同,通过专家的参与,我们能够处理错误指定的模型。此外,实证结果显示更好的后验估计比现有的方法,当模拟预算是有限的。

英文摘要:

Approximate Bayesian computation (ABC) is a popular likelihood-free inference method for models with intractable likelihood functions. As ABC methods usually rely on comparing summary statistics of observed and simulated data, the choice of the statistics is crucial. This choice involves a trade-off between loss of information and dimensionality reduction, and is often determined based on domain knowledge. However, handcrafting and selecting suitable statistics is a laborious task involving multiple trial-and-error steps. In this work, we introduce an active learning method for ABC statistics selection which reduces the domain expert's work considerably. By involving the experts, we are able to handle misspecified models, unlike the existing dimension reduction methods. Moreover, empirical results show better posterior estimates than with existing methods, when the simulation budget is limited.

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。

↑