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 2301.02729cs.LGstat.ML
收藏

多输出可学习性的刻画

A Characterization of Multioutput Learnability

University of Michigan(密歇根大学)

Vinod Raman, Unique Subedi, Ambuj Tewari

AI总结:

针对批量、在线及扩展的bandit反馈设置下的多输出函数类学习问题,证明多输出函数类可学习当且仅当其每个单输出限制可学习,完整刻画了多标签分类与多输出回归的可学习性。

摘要:

我们研究批量和在线设置下多输出函数类的学习问题。在两种设置中,我们证明多输出函数类可学习当且仅当其每个单输出限制函数类可学习。这为批量和在线设置下多标签分类与多输出回归的可学习性提供了完整刻画。作为扩展,我们还研究了bandit反馈设置下的多标签可学习性,并展示了与全反馈设置类似的刻画。

英文摘要:

We consider the problem of learning multioutput function classes in the batch and online settings. In both settings, we show that a multioutput function class is learnable if and only if each single-output restriction of the function class is learnable. This provides a complete characterization of the learnability of multilabel classification and multioutput regression in both batch and online settings. As an extension, we also consider multilabel learnability in the bandit feedback setting and show a similar characterization as in the full-feedback setting.

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。

↑