arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.01123stat.MLcs.CVcs.LG
收藏

表示学习中的互信息梯度估计

Mutual Information Gradient Estimation for Representation Learning

University of Electronic Science and Technology of China(电子科技大学);Peng Cheng Laboratory(鹏城实验室);University of Texas at Austin(德克萨斯大学奥斯汀分校);Harbin Institute of Technology(哈尔滨工业大学)

Liangjian Wen, Yiji Zhou, Lirong He, Mingyuan Zhou, Zenglin Xu

摘要:

互信息在表征学习中起着重要的作用。然而,不幸的是,MI是棘手的连续和高维设置。最近的进展建立了易于处理和可扩展的MI估计,发现有用的表示。然而,大多数现有的方法是不能够提供一个准确的估计MI与低方差时,MI是大的。我们认为,直接估计MI的梯度是更有吸引力的表示学习比估计MI本身。为此,我们提出了互信息梯度估计(MIGE)表示学习的基础上的分数估计的隐式分布。MIGE在高维和大MI的情况下表现出一个紧而光滑的MI梯度估计。我们扩展了MIGE在基于InfoMax的深度表示的无监督学习和信息瓶颈方法中的应用。实验结果表明,在学习有用的表示显着的性能改善。

英文摘要:

Mutual Information (MI) plays an important role in representation learning. However, MI is unfortunately intractable in continuous and high-dimensional settings. Recent advances establish tractable and scalable MI estimators to discover useful representation. However, most of the existing methods are not capable of providing an accurate estimation of MI with low-variance when the MI is large. We argue that directly estimating the gradients of MI is more appealing for representation learning than estimating MI in itself. To this end, we propose the Mutual Information Gradient Estimator (MIGE) for representation learning based on the score estimation of implicit distributions. MIGE exhibits a tight and smooth gradient estimation of MI in the high-dimensional and large-MI settings. We expand the applications of MIGE in both unsupervised learning of deep representations based on InfoMax and the Information Bottleneck method. Experimental results have indicated significant performance improvement in learning useful representation.

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。

↑