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 1604.05024cs.LGcs.AI
收藏

PROXTONE和PROXTONE $^+$用于大规模稀疏模型快速学习的实证研究

Empirical study of PROXTONE and PROXTONE$^+$ for Fast Learning of Large Scale Sparse Models

Fujitsu Research & Development Center(富士通研发中心)

Ziqiang Shi, Rujie Liu

摘要:

PROXTONE是求解大规模非光滑凸优化问题\cite{shi2015large}的一种新颖、快速的方法。在这项工作中,我们尝试使用PROXTONE方法来解决大规模\emph{non-smooth non-convex}问题,例如用于嵌入式或移动终端的稀疏深度神经网络(稀疏DNN)或稀疏卷积神经网络(稀疏CNN)的训练。PROXTONE的收敛速度比一阶方法快得多,而一阶方法易于推导和控制解的稀疏性。因此,在某些应用中,为了快速训练稀疏模型,我们提出结合两种方法的优点,即在前几个时期使用PROXTONE来达到最优解的邻域,然后在随后的训练中使用一阶方法来探索稀疏的可能性。我们将这种方法称为PROXTONE plus(PROXTONE $^+$)。在我们的实验中,PROXTONE和PROXTONE $^+$都进行了测试,并表明这两种方法至少在不同的稀疏模型学习问题上将收敛速度提高了两倍,同时将DNN模型的大小减少到0.5%。所有算法的源代码可根据要求提供。

英文摘要:

PROXTONE is a novel and fast method for optimization of large scale non-smooth convex problem \cite{shi2015large}. In this work, we try to use PROXTONE method in solving large scale \emph{non-smooth non-convex} problems, for example training of sparse deep neural network (sparse DNN) or sparse convolutional neural network (sparse CNN) for embedded or mobile device. PROXTONE converges much faster than first order methods, while first order method is easy in deriving and controlling the sparseness of the solutions. Thus in some applications, in order to train sparse models fast, we propose to combine the merits of both methods, that is we use PROXTONE in the first several epochs to reach the neighborhood of an optimal solution, and then use the first order method to explore the possibility of sparsity in the following training. We call such method PROXTONE plus (PROXTONE$^+$). Both PROXTONE and PROXTONE$^+$ are tested in our experiments, and which demonstrate both methods improved convergence speed twice as fast at least on diverse sparse model learning problems, and at the same time reduce the size to 0.5\% for DNN models. The source of all the algorithms is available upon request.

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。

↑