arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1204.2069stat.MLcs.LG
收藏

潜变量基于分布估计的渐近精度

Asymptotic Accuracy of Distribution-Based Estimation for Latent Variables

Tokyo Institute of Technology(东京工业大学)

Keisuke Yamazaki

摘要:

层次统计模型在信息科学和数据工程中有着广泛的应用。模型由两种类型的变量组成:代表给定数据的可观察变量和不可观察标签的潜变量。模型的渐近分析在评估学习过程中起着重要的作用;分析的结果不仅适用于理论,而且适用于实际情况,如最佳模型选择和主动学习。有许多关于泛化误差的研究,泛化误差衡量可观测变量的预测精度。然而,估计的潜变量的准确性尚未阐明。为了定量评估这一点,本文制定了基于分布的函数的潜在变量的估计误差。分析了极大似然和贝叶斯方法的渐近行为。

英文摘要:

Hierarchical statistical models are widely employed in information science and data engineering. The models consist of two types of variables: observable variables that represent the given data and latent variables for the unobservable labels. An asymptotic analysis of the models plays an important role in evaluating the learning process; the result of the analysis is applied not only to theoretical but also to practical situations, such as optimal model selection and active learning. There are many studies of generalization errors, which measure the prediction accuracy of the observable variables. However, the accuracy of estimating the latent variables has not yet been elucidated. For a quantitative evaluation of this, the present paper formulates distribution-based functions for the errors in the estimation of the latent variables. The asymptotic behavior is analyzed for both the maximum likelihood and the Bayes methods.

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。

↑