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 2007.12815cs.LGcs.DSstat.ML
收藏

从玻尔兹曼机到神经网络,再回来

From Boltzmann Machines to Neural Networks and Back Again

Microsoft Research NYC(微软纽约研究院);University of Texas at Austin(德克萨斯大学奥斯汀分校);MIT(麻省理工学院)

Surbhi Goel, Adam Klivans, Frederic Koehler

摘要:

图形模型是对高维数据建模的有力工具,但在存在潜在变量的情况下学习图形模型是众所周知的困难。在这项工作中,我们给出了新的结果学习限制玻尔兹曼机,可能是最好的研究类的潜变量模型。我们的研究结果是基于新的连接学习两层神经网络下$\ell_{\infty}$有界输入,对于这两个问题,我们给出了几乎最优的结果下稀疏奇偶噪声的约束硬度。利用RBM和前馈网络之间的联系,我们还启动了$supervised~RBMs$的理论研究[Hinton,2012],这是一种神经网络学习的版本,它将从底层图形模型中导出的分布假设与未知函数类的架构相耦合。然后,我们给出了一个算法,学习一个自然类的监督RBM更好的运行时间比它的相关类的网络没有分布的假设。

英文摘要:

Graphical models are powerful tools for modeling high-dimensional data, but learning graphical models in the presence of latent variables is well-known to be difficult. In this work we give new results for learning Restricted Boltzmann Machines, probably the most well-studied class of latent variable models. Our results are based on new connections to learning two-layer neural networks under $\ell_{\infty}$ bounded input; for both problems, we give nearly optimal results under the conjectured hardness of sparse parity with noise. Using the connection between RBMs and feedforward networks, we also initiate the theoretical study of $supervised~RBMs$ [Hinton, 2012], a version of neural-network learning that couples distributional assumptions induced from the underlying graphical model with the architecture of the unknown function class. We then give an algorithm for learning a natural class of supervised RBMs with better runtime than what is possible for its related class of networks without distributional assumptions.

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。

↑