arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.01449stat.MLcs.LG
收藏

自编码器无监督和半监督学习的泛化界

Generalization Bounds For Unsupervised and Semi-Supervised Learning With Autoencoders

Viterbi Faculty of Electrical Engineering, Technion - Israel Institute of Technology(以色列理工学院维特比电气与电子工程学院)

Baruch Epstein, Ron Meir

摘要:

自编码器广泛用于无监督学习和半监督学习中的正则化方案。然而,他们的泛化性能和他们可以帮助监督学习的方式的理论理解一直缺乏。我们利用深度学习泛化理论的最新进展,以及新的重建损失,为自动编码器提供泛化界。据我们所知,这是第一次这样的约束。我们进一步表明,在适当的假设下,具有良好泛化性能的自编码器可以改善任何半监督学习方案。我们支持我们的理论结果与实证证明。

英文摘要:

Autoencoders are widely used for unsupervised learning and as a regularization scheme in semi-supervised learning. However, theoretical understanding of their generalization properties and of the manner in which they can assist supervised learning has been lacking. We utilize recent advances in the theory of deep learning generalization, together with a novel reconstruction loss, to provide generalization bounds for autoencoders. To the best of our knowledge, this is the first such bound. We further show that, under appropriate assumptions, an autoencoder with good generalization properties can improve any semi-supervised learning scheme. We support our theoretical results with empirical demonstrations.

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。

↑