arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.05916cs.LG
收藏

多任务学习的局部Rademacher复杂性学习保证

Local Rademacher Complexity-based Learning Guarantees for Multi-Task Learning

University of Central Florida(中佛罗里达大学);Florida Institute of Technology(佛罗里达理工学院)

Niloofar Yousefi, Yunwen Lei, Marius Kloft, Mansooreh Mollaghasemi, Georgios Anagnostopoulos

摘要:

我们展示了多任务学习(MTL)的Talagrand型浓度不等式,使用该不等式,我们建立了MTL的局部Rademacher复杂性(LRC)的分布和数据依赖版本的急剧超额风险界限。我们还给出了一个新的约束的LRC的范数正则化以及强凸假设类,这不仅适用于MTL,但也标准的i.i.d.设置.结合这两个结果,现在可以轻松推导出许多著名MTL方法的超额风险的快速界限,包括--正如我们所展示的--Schatten范数、群范数和图正则化MTL。导出的界限反映了一个关系akeen的渐近收敛速度的守恒定律。正是这种关系允许在较慢的利率上进行权衡。当与通过传统的全局Rademacher分析获得的速率相比时,相对于每个任务的可用样本数,更快速率的任务数。

英文摘要:

We show a Talagrand-type concentration inequality for Multi-Task Learning (MTL), using which we establish sharp excess risk bounds for MTL in terms of distribution- and data-dependent versions of the Local Rademacher Complexity (LRC). We also give a new bound on the LRC for norm regularized as well as strongly convex hypothesis classes, which applies not only to MTL but also to the standard i.i.d. setting. Combining both results, one can now easily derive fast-rate bounds on the excess risk for many prominent MTL methods, including---as we demonstrate---Schatten-norm, group-norm, and graph-regularized MTL. The derived bounds reflect a relationship akeen to a conservation law of asymptotic convergence rates. This very relationship allows for trading off slower rates w.r.t. the number of tasks for faster rates with respect to the number of available samples per task, when compared to the rates obtained via a traditional, global Rademacher analysis.

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。

↑