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 2302.07409cs.LGcs.CCquant-phstat.ML
收藏

超越批量二分类的量子学习理论

Quantum Learning Theory Beyond Batch Binary Classification

Department of Mathematics, University of Michigan(数学系,密歇根大学);Department of Statistics, University of Michigan(统计学系,密歇根大学);Department of Electrical Engineering and Computer Science, University of Michigan(电气工程与计算机科学系,密歇根大学)

Preetham Mohan, Ambuj Tewari

AI总结:

该研究将量子批量布尔学习样本复杂度与经典样本复杂度同阶的结论,拓展至批量多分类、在线布尔及在线多分类学习场景,并首次提出带量子样本的在线学习模型。

摘要:

Arunachalam和de Wolf(2018)证明,在可实现与不可知(agnostic)场景下,布尔函数的量子批量学习的样本复杂度,与对应的经典样本复杂度具有相同的形式与阶数。本文将这一表面上令人意外的结论拓展至批量多分类学习、在线布尔学习以及在线多分类学习场景。针对在线学习的研究结果,我们首先考虑了Dawid和Tewari(2022)提出的经典模型的自适应敌手变体。随后,据我们所知,我们首次提出了采用量子样本的在线学习模型。

英文摘要:

Arunachalam and de Wolf (2018) showed that the sample complexity of quantum batch learning of boolean functions, in the realizable and agnostic settings, has the same form and order as the corresponding classical sample complexities. In this paper, we extend this, ostensibly surprising, message to batch multiclass learning, online boolean learning, and online multiclass learning. For our online learning results, we first consider an adaptive adversary variant of the classical model of Dawid and Tewari (2022). Then, we introduce the first (to the best of our knowledge) model of online learning with quantum examples.

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。

↑