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 2402.13400stat.MLcs.LG
收藏

自指导学习的维度

The Dimension of Self-Directed Learning

Purdue University(普渡大学)

Pramith Devulapalli, Steve Hanneke

AI总结:

本文提出维度$SDdim$,通过“标注博弈”精确刻画自指导学习的错误界,并在多种概念类上计算该维度,同时分析了自指导学习与离线序列学习模型的可学习性差距及不可知设置下的上下界。

摘要:

理解自指导学习复杂性自20世纪90年代初以来一直是在线学习理论界关注的重要问题。在该框架中,与对抗性在线学习设置不同,学习者可以在进行预测时自适应地选择其下一个数据点。在本文中,我们研究了二分类和多分类设置下的自指导学习复杂性,并提出了一个维度,即$SDdim$,它精确刻画了任意概念类的自指导学习错误界。$SDdim$背后的直觉可以理解为一个称为“标注博弈”的双人博弈。借助这个双人博弈,我们在大量示例上计算了$SDdim$,在轴对齐矩形、VC维为$1$的类以及线性分隔器上取得了显著结果。我们展示了几种可学习性差距,重点关注自指导学习和包含最优或最差排序的离线序列学习模型。最后,我们将分析扩展到自指导二分类不可知设置,并推导出上界和下界。

英文摘要:

Understanding the self-directed learning complexity has been an important problem that has captured the attention of the online learning theory community since the early 1990s. Within this framework, the learner is allowed to adaptively choose its next data point in making predictions unlike the setting in adversarial online learning. In this paper, we study the self-directed learning complexity in both the binary and multi-class settings, and we develop a dimension, namely $SDdim$, that exactly characterizes the self-directed learning mistake-bound for any concept class. The intuition behind $SDdim$ can be understood as a two-player game called the "labelling game". Armed with this two-player game, we calculate $SDdim$ on a whole host of examples with notable results on axis-aligned rectangles, VC dimension $1$ classes, and linear separators. We demonstrate several learnability gaps with a central focus on self-directed learning and offline sequence learning models that include either the best or worst ordering. Finally, we extend our analysis to the self-directed binary agnostic setting where we derive upper and lower bounds.

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。

↑