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 2310.18786cs.LGcs.DS
收藏

一种用于不可知主动学习的竞争性算法

A Competitive Algorithm for Agnostic Active Learning

University of Texas at Austin(德克萨斯大学奥斯汀分校)

Eric Price, Yihan Zhou

AI总结:

本文提出一种竞争性主动不可知学习算法,以$O(m^*\log|H|)$查询实现$O(η)$误差,并证明超越该开销是NP困难的。

摘要:

对于某些假设类别和输入分布,主动不可知学习所需的样本量比被动学习呈指数级减少;而对于其他类别和分布,它几乎没有改进。最流行的不可知主动学习算法以称为分歧系数的参数来表达其性能,但已知这些算法在某些输入上效率低下。我们采用不同的方法处理不可知主动学习,得到一种与任何二元假设类别$H$和$X$上的分布$D_X$的最优算法具有竞争性的算法。特别地,如果任何算法可以使用$m^*$次查询获得$O(η)$误差,那么我们的算法使用$O(m^* \log |H|)$次查询获得$O(η)$误差。我们的算法属于Dasgupta [2004]的基于分裂的方法,该方法在可实现($η=0$)设置中获得了类似的结果。我们还表明,在一般情况下,比我们算法的$O(\log |H|)$开销做得更好是NP困难的。

英文摘要:

For some hypothesis classes and input distributions, active agnostic learning needs exponentially fewer samples than passive learning; for other classes and distributions, it offers little to no improvement. The most popular algorithms for agnostic active learning express their performance in terms of a parameter called the disagreement coefficient, but it is known that these algorithms are inefficient on some inputs. We take a different approach to agnostic active learning, getting an algorithm that is competitive with the optimal algorithm for any binary hypothesis class $H$ and distribution $D_X$ over $X$. In particular, if any algorithm can use $m^*$ queries to get $O(η)$ error, then our algorithm uses $O(m^* \log |H|)$ queries to get $O(η)$ error. Our algorithm lies in the vein of the splitting-based approach of Dasgupta [2004], which gets a similar result for the realizable ($η= 0$) setting. We also show that it is NP-hard to do better than our algorithm's $O(\log |H|)$ overhead in general.

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。

↑