arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02150stat.MLcs.LG
收藏

基于最优贝叶斯迁移学习的稳健重要性抽样误差估计

Robust Importance Sampling for Error Estimation in the Context of Optimal Bayesian Transfer Learning

Texas A&M University(德克萨斯农工大学);Brookhaven National Laboratory(布鲁克海文国家实验室)

Omar Maddouri, Xiaoning Qian, Francis J. Alexander, Edward R. Dougherty, Byung-Jun Yoon

摘要:

分类一直是构建智能系统的主要任务,因为它可以在不确定性下做出决策。分类器设计的目的是从训练数据中构建模型,以显式或隐式地表示特征标签分布。在许多科学或临床环境中,训练数据通常是有限的,这使得设计准确的分类器和评估其分类错误极具挑战性。虽然迁移学习(TL)可以通过合并来自相关源域的数据来改善不同目标域中的学习来缓解这个问题,但它在性能评估方面很少受到关注,特别是在错误估计方面。在本文中,我们填补了这一空白调查的背景下,贝叶斯范式的分类误差估计的知识转移。我们引入了一类新的贝叶斯最小均方误差(MMSE)估计的最优贝叶斯迁移学习(OBTL),这使得严格的分类误差评估下的不确定性在小样本设置。使用蒙特卡罗重要性抽样,我们采用建议的估计,以评估分类器,跨越不同的学习能力的一个广泛的家庭的分类精度。基于合成数据和真实世界RNA测序(RNA-seq)数据的实验结果表明,我们提出的OBTL误差估计方案明显优于标准误估计,特别是在小样本设置中,通过利用其他相关领域的数据。

英文摘要:

Classification has been a major task for building intelligent systems as it enables decision-making under uncertainty. Classifier design aims at building models from training data for representing feature-label distributions--either explicitly or implicitly. In many scientific or clinical settings, training data are typically limited, which makes designing accurate classifiers and evaluating their classification error extremely challenging. While transfer learning (TL) can alleviate this issue by incorporating data from relevant source domains to improve learning in a different target domain, it has received little attention for performance assessment, notably in error estimation. In this paper, we fill this gap by investigating knowledge transferability in the context of classification error estimation within a Bayesian paradigm. We introduce a novel class of Bayesian minimum mean-square error (MMSE) estimators for optimal Bayesian transfer learning (OBTL), which enables rigorous evaluation of classification error under uncertainty in a small-sample setting. Using Monte Carlo importance sampling, we employ the proposed estimator to evaluate the classification accuracy of a broad family of classifiers that span diverse learning capabilities. Experimental results based on both synthetic data as well as real-world RNA sequencing (RNA-seq) data show that our proposed OBTL error estimation scheme clearly outperforms standard error estimators, especially in a small-sample setting, by tapping into the data from other relevant domains.

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。

↑