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 2201.09433cs.LGcs.CCstat.ML
收藏

主动学习多项式阈值函数

Active Learning Polynomial Threshold Functions

MIT(麻省理工学院);UCSD(加州大学圣地亚哥分校);Stanford University(斯坦福大学);Columbia University(哥伦比亚大学)

Omri Ben-Eliezer, Max Hopkins, Chutong Yang, Hantao Yu

摘要:

我们开始了主动学习多项式阈值函数(PTFs)的研究。虽然传统的下限意味着,即使是单变量二次不能非平凡地积极学习,我们表明,允许学习者基本访问的衍生物的基础分类规避这个问题,并导致一个计算效率高的算法主动学习度$d$单变量PTFs在$\tilde{O}(d^3\log(1/\varepsilonδ))$查询。我们还提供了接近最佳的算法和分析主动学习PTFs在几个平均情况下设置。最后,我们证明,获得衍生物是不够的主动学习多变量PTFs,即使只有两个变量。

英文摘要:

We initiate the study of active learning polynomial threshold functions (PTFs). While traditional lower bounds imply that even univariate quadratics cannot be non-trivially actively learned, we show that allowing the learner basic access to the derivatives of the underlying classifier circumvents this issue and leads to a computationally efficient algorithm for active learning degree-$d$ univariate PTFs in $\tilde{O}(d^3\log(1/\varepsilonδ))$ queries. We also provide near-optimal algorithms and analyses for active learning PTFs in several average case settings. Finally, we prove that access to derivatives is insufficient for active learning multivariate PTFs, even those of just two variables.

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。

↑