arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.02552cs.LGcs.AIstat.ML
收藏

主动覆盖

Active Covering

Google Research(谷歌研究院)

Heinrich Jiang, Afshin Rostamizadeh

摘要:

我们分析了主动覆盖的问题,其中学习者被赋予一个未标记的数据集,并可以顺序标记查询示例。目标是在最少的标签查询总数中对所有的正例进行标签查询。我们表明,在标准的非参数假设下,一个经典的支持估计可以被重新利用作为一个离线算法,实现额外的查询成本相比,最佳的学习者,$\widetildeΘ(n^{D/(D+1)})$,其中$n$是数据点的数量和$D$是维度。然后,我们提供了一个简单的主动学习方法,达到了改进的额外查询成本的$\widetilde{O}(n^{(D-1)/D})$。此外,所提出的算法只需要访问正标记的示例,这在某些设置中提供了额外的计算和隐私优势。最后,我们表明,主动学习方法始终优于离线方法,以及各种基准上的广泛的基于图像的数据集。

英文摘要:

We analyze the problem of active covering, where the learner is given an unlabeled dataset and can sequentially label query examples. The objective is to label query all of the positive examples in the fewest number of total label queries. We show under standard non-parametric assumptions that a classical support estimator can be repurposed as an offline algorithm attaining an excess query cost of $\widetildeΘ(n^{D/(D+1)})$ compared to the optimal learner, where $n$ is the number of datapoints and $D$ is the dimension. We then provide a simple active learning method that attains an improved excess query cost of $\widetilde{O}(n^{(D-1)/D})$. Furthermore, the proposed algorithms only require access to the positive labeled examples, which in certain settings provides additional computational and privacy benefits. Finally, we show that the active learning method consistently outperforms offline methods as well as a variety of baselines on a wide range of benchmark image-based datasets.

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。

↑