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 1702.03380cs.LGcs.DC
收藏

通过图优化训练深度神经网络

Training Deep Neural Networks via Optimization Over Graphs

University of Technology, Sydney(悉尼科技大学);Victoria University of Wellington(惠灵顿维多利亚大学)

Guoqiang Zhang, W. Bastiaan Kleijn

摘要:

在这项工作中,我们提出了通过图上的分布式优化来训练深度神经网络。考虑两个非线性函数:整流线性单元(ReLU)和具有上下截止值的线性单元(DCutLU)。通过使用一组松弛变量显式表示ReLU或DCutLU来实现图上的问题重构。然后,我们应用交替方向的乘法器(ADMM)更新的权重的网络逐层解决子问题的重新制定的问题。实证结果表明,基于ADMM的方法是不太敏感的过度拟合比随机梯度下降(SGD)和亚当的方法。

英文摘要:

In this work, we propose to train a deep neural network by distributed optimization over a graph. Two nonlinear functions are considered: the rectified linear unit (ReLU) and a linear unit with both lower and upper cutoffs (DCutLU). The problem reformulation over a graph is realized by explicitly representing ReLU or DCutLU using a set of slack variables. We then apply the alternating direction method of multipliers (ADMM) to update the weights of the network layerwise by solving subproblems of the reformulated problem. Empirical results suggest that the ADMM-based method is less sensitive to overfitting than the stochastic gradient descent (SGD) and Adam 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。

↑