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 1404.6674cs.LG
收藏

机器学习的一阶算法比较

A Comparison of First-order Algorithms for Machine Learning

Graz University of Technology(格拉茨技术大学)

Yu Wei, Pock Thomas

摘要:

利用优化算法解决机器学习问题是当前科学领域的主流之一。在这项工作中,我们展示了一些国家的最先进的凸优化问题的一阶优化算法在机器学习的全面比较。我们专注于几个光滑和非光滑的机器学习问题的损失函数加上正则化。整体实验结果表明,原始-对偶算法在解决机器学习问题的优势,从易于构建,运行时间和准确性的角度。

英文摘要:

Using an optimization algorithm to solve a machine learning problem is one of mainstreams in the field of science. In this work, we demonstrate a comprehensive comparison of some state-of-the-art first-order optimization algorithms for convex optimization problems in machine learning. We concentrate on several smooth and non-smooth machine learning problems with a loss function plus a regularizer. The overall experimental results show the superiority of primal-dual algorithms in solving a machine learning problem from the perspectives of the ease to construct, running time and accuracy.

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。

↑