arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.09030cs.LGcs.AIcs.CV
收藏

Meta-无监督学习:一种有监督的无监督学习方法

Meta-Unsupervised-Learning: A supervised approach to unsupervised learning

Vikas K. Garg, Adam Tauman Kalai

摘要:

我们引入了一种新的范式来研究无监督学习,将无监督学习归结为监督学习。具体来说,我们通过利用从先前的、可能是异构的监督学习任务中获得的知识来减轻无监督决策中的主观性。我们通过对几个无监督问题的全面阐述和详细实验来展示我们框架的多功能性,这些问题包括(a)聚类,(b)离群点检测和(c)在元无监督学习的共同保护伞下的相似性预测。我们还提供了严格的PAC不可知的界限,建立我们的框架的理论基础,并表明我们的框架的元聚类规避克莱因伯格的不可能定理聚类。

英文摘要:

We introduce a new paradigm to investigate unsupervised learning, reducing unsupervised learning to supervised learning. Specifically, we mitigate the subjectivity in unsupervised decision-making by leveraging knowledge acquired from prior, possibly heterogeneous, supervised learning tasks. We demonstrate the versatility of our framework via comprehensive expositions and detailed experiments on several unsupervised problems such as (a) clustering, (b) outlier detection, and (c) similarity prediction under a common umbrella of meta-unsupervised-learning. We also provide rigorous PAC-agnostic bounds to establish the theoretical foundations of our framework, and show that our framing of meta-clustering circumvents Kleinberg's impossibility theorem for clustering.

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。

↑