arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1507.01972stat.MLcs.LG
收藏

玻尔兹曼机的Wasserstein训练

Wasserstein Training of Boltzmann Machines

Korea University(高丽大学);Technische Universität Berlin(柏林工业大学);Kyoto University(京都大学)

Grégoire Montavon, Klaus-Robert Müller, Marco Cuturi

摘要:

玻尔兹曼机提供了一个有用的框架来学习现实世界中发生的高度复杂,多模态和多尺度的数据分布。学习其参数的默认方法包括最小化从训练样本到玻尔兹曼模型的Kullback-Leibler(KL)发散。在这项工作中,我们提出了一种新的方法玻尔兹曼训练,假设观察之间的一个有意义的度量。该度量可以由分布之间的瓦瑟斯坦距离表示,我们推导出相对于模型参数的梯度。这个新的Wasserstein目标的最小化导致生成模型在考虑度量时更好,并且具有类簇结构。我们展示了这些模型在数据完成和去噪方面的实际潜力,其中观测之间的度量起着至关重要的作用。

英文摘要:

The Boltzmann machine provides a useful framework to learn highly complex, multimodal and multiscale data distributions that occur in the real world. The default method to learn its parameters consists of minimizing the Kullback-Leibler (KL) divergence from training samples to the Boltzmann model. We propose in this work a novel approach for Boltzmann training which assumes that a meaningful metric between observations is given. This metric can be represented by the Wasserstein distance between distributions, for which we derive a gradient with respect to the model parameters. Minimization of this new Wasserstein objective leads to generative models that are better when considering the metric and that have a cluster-like structure. We demonstrate the practical potential of these models for data completion and denoising, for which the metric between observations plays a crucial role.

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。

↑