arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07402cs.LGcs.ITmath.IT
收藏

不同自动编码器的信息流

Information flows of diverse autoencoders

Seoul National University(首尔国立大学);Korea Institute for Advanced Study(韩国高等研究院)

Sungyeop Lee, Junghyo Jo

摘要:

深度学习在各个领域的出色表现一直是一个基本的问题,可以使用信息论进行潜在的检查,该理论将学习过程解释为信息的传输和压缩。输入-隐藏-输出层之间的互信息的信息平面分析展示了拟合和压缩两个不同的学习阶段。压缩阶段是否有必要对从训练数据中提取的输入-输出关系进行概括是有争议的。在这项研究中,我们调查了这一点,通过实验与各种自动编码器和评估其信息处理阶段与一个准确的基于核的估计互信息。如果有足够的训练数据,vanilla自动编码器演示了压缩阶段,在对隐藏活动进行稀疏正则化后,压缩阶段被放大。然而,我们发现,压缩阶段并不普遍观察到不同种类的自编码器,包括变分自编码器,有特殊的约束网络权重或流形的隐藏空间。这些类型的自编码器表现出完美的泛化能力的测试数据,而不需要压缩阶段。因此,我们得出结论,压缩阶段是不必要的推广表示学习。

英文摘要:

The outstanding performance of deep learning in various fields has been a fundamental query, which can be potentially examined using information theory that interprets the learning process as the transmission and compression of information. Information plane analyses of the mutual information between the input-hidden-output layers demonstrated two distinct learning phases of fitting and compression. It is debatable if the compression phase is necessary to generalize the input-output relations extracted from training data. In this study, we investigated this through experiments with various species of autoencoders and evaluated their information processing phase with an accurate kernel-based estimator of mutual information. Given sufficient training data, vanilla autoencoders demonstrated the compression phase, which was amplified after imposing sparsity regularization for hidden activities. However, we found that the compression phase is not universally observed in different species of autoencoders, including variational autoencoders, that have special constraints on network weights or manifold of hidden space. These types of autoencoders exhibited perfect generalization ability for test data without requiring the compression phase. Thus, we conclude that the compression phase is not necessary for generalization in representation learning.

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。

↑