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 1807.00172math.OCcs.LGstat.ML
收藏

解决深度神经网络模型产生的最优化问题的算法:平滑问题

Algorithms for solving optimization problems arising from deep neural net models: smooth problems

Vyacheslav Kungurtsev, Tomas Pevny

摘要:

结合多层学习网络的机器学习模型已被视为为各种分类问题提供有效的模型。然而,求解使经验风险最小化的最优向量的所得最优化问题是高度非线性的。这对应用和开发用于解决该问题的适当优化算法提出了挑战。在本文中,我们总结了所涉及的主要挑战,并提出了一个基于牛顿的方法纳入负曲率方向的情况下,包括有前途的数值结果所产生的数据安全异常检测。

英文摘要:

Machine Learning models incorporating multiple layered learning networks have been seen to provide effective models for various classification problems. The resulting optimization problem to solve for the optimal vector minimizing the empirical risk is, however, highly nonlinear. This presents a challenge to application and development of appropriate optimization algorithms for solving the problem. In this paper, we summarize the primary challenges involved and present the case for a Newton-based method incorporating directions of negative curvature, including promising numerical results on data arising from security anomally deetection.

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。

↑