arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.09798stat.MLcs.LG
收藏

宽随机网络:高斯极限和PAC-Bayesian训练

Wide stochastic networks: Gaussian limit and PAC-Bayesian training

University of Oxford(牛津大学)

Eugenio Clerico, George Deligiannidis, Arnaud Doucet

摘要:

无限宽度的限制允许在过参数化神经网络的分析研究中进行实质性的简化。通过适当的随机初始化,一个非常大的网络表现出近似高斯的行为。在目前的工作中,我们建立了一个简单的随机结构,其参数是随机变量,在训练前和训练过程中保持类似的结果。输出分布的显式评估允许PAC-贝叶斯训练过程直接优化泛化边界。对于一个大型但有限宽度的网络,我们在MNIST上凭经验证明,这种训练方法可以优于标准的PAC-Bayesian方法。

英文摘要:

The limit of infinite width allows for substantial simplifications in the analytical study of over-parameterised neural networks. With a suitable random initialisation, an extremely large network exhibits an approximately Gaussian behaviour. In the present work, we establish a similar result for a simple stochastic architecture whose parameters are random variables, holding both before and during training. The explicit evaluation of the output distribution allows for a PAC-Bayesian training procedure that directly optimises the generalisation bound. For a large but finite-width network, we show empirically on MNIST that this training approach can outperform standard PAC-Bayesian methods.

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。

↑