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 1106.4251cs.LGstat.ML
收藏

任意抽样分布下的加权迹范数学习

Learning with the Weighted Trace-norm under Arbitrary Sampling Distributions

University of Chicago(芝加哥大学);Massachusetts Institute of Technology(麻省理工学院);Microsoft Research New England(微软新英格兰研究院);Toyota Technological Institute at Chicago(芝加哥丰田技术研究院)

Rina Foygel, Ruslan Salakhutdinov, Ohad Shamir, Nathan Srebro

摘要:

我们提供了严格的保证学习与加权跟踪范数下任意采样分布。我们表明,标准加权跟踪范数可能会失败时,抽样分布不是产品分布(即当行和列索引不独立选择),提出了一个修正的变体,我们建立了强大的学习保证,并证明它在实践中更好地工作。我们提供的保证时,加权的真实或经验的抽样分布,并建议,即使真实的分布是已知的(或均匀),加权的经验分布可能是有益的。

英文摘要:

We provide rigorous guarantees on learning with the weighted trace-norm under arbitrary sampling distributions. We show that the standard weighted trace-norm might fail when the sampling distribution is not a product distribution (i.e. when row and column indexes are not selected independently), present a corrected variant for which we establish strong learning guarantees, and demonstrate that it works better in practice. We provide guarantees when weighting by either the true or empirical sampling distribution, and suggest that even if the true distribution is known (or is uniform), weighting by the empirical distribution may be beneficial.

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。

↑