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 0910.0610cs.LGstat.ML
收藏

矩阵学习的正则化技术

Regularization Techniques for Learning with Matrices

The Wharton School(沃顿商学院);University of Pennsylvania(宾夕法尼亚大学);School of Computer Sc. & Eng.(计算机科学与工程学院);The Hebrew University of Jerusalem(希伯来大学);Computer Science Department(计算机科学系);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Sham M. Kakade, Shai Shalev-Shwartz, Ambuj Tewari

摘要:

有越来越多的学习问题,这是很自然的组织成矩阵的参数,以便适当地正则化的参数下一些矩阵范数(为了施加一些更复杂的先验知识)。这项工作描述和分析了一个系统的方法来构建这种基于矩阵的正则化方法。特别是,我们专注于一个给定问题的基本统计特性如何帮助我们决定哪个正则化函数是合适的。我们的方法是基于已知的对偶事实:一个函数是强凸的一些规范,当且仅当其共轭函数是强光滑的对偶规范。这个结果已经被发现是一个关键组成部分,在推导和分析几个学习算法。我们证明了这个框架的潜力,通过推导新的泛化和遗憾的界限多任务学习,多类学习和内核学习。

英文摘要:

There is growing body of learning problems for which it is natural to organize the parameters into matrix, so as to appropriately regularize the parameters under some matrix norm (in order to impose some more sophisticated prior knowledge). This work describes and analyzes a systematic method for constructing such matrix-based, regularization methods. In particular, we focus on how the underlying statistical properties of a given problem can help us decide which regularization function is appropriate. Our methodology is based on the known duality fact: that a function is strongly convex with respect to some norm if and only if its conjugate function is strongly smooth with respect to the dual norm. This result has already been found to be a key component in deriving and analyzing several learning algorithms. We demonstrate the potential of this framework by deriving novel generalization and regret bounds for multi-task learning, multi-class learning, and kernel learning.

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。

↑