arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1605.00529stat.MLcs.LG
收藏

无监督学习中空间、时间、数据和风险的权衡

Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning

ETH Zürich(苏黎世联邦理工学院);University of California, San Diego(加利福尼亚大学圣迭戈分校);Yale University(耶鲁大学)

Mario Lucic, Mesrob I. Ohannessian, Amin Karbasi, Andreas Krause

摘要:

面对海量数据,是否有可能权衡(统计)风险、(计算)空间和时间?这一挑战是大规模机器学习的核心。使用k-means聚类作为一个典型的无监督学习问题,我们展示了如何从战略上总结数据(控制空间),以便在数据由概率模型生成时权衡风险和时间。我们的总结是基于计算几何的核心结构。我们还开发了一个算法,TRAM,在实践中导航的空间/时间/数据/风险权衡。特别是,我们表明,对于一个固定的风险(或数据大小),随着数据大小的增加(分别。风险增加)TRAM的运行时间减少。我们在真实数据集上进行的大量实验证明了这种权衡的存在性和实用性,不仅适用于k均值,而且适用于高斯混合模型。

英文摘要:

Faced with massive data, is it possible to trade off (statistical) risk, and (computational) space and time? This challenge lies at the heart of large-scale machine learning. Using k-means clustering as a prototypical unsupervised learning problem, we show how we can strategically summarize the data (control space) in order to trade off risk and time when data is generated by a probabilistic model. Our summarization is based on coreset constructions from computational geometry. We also develop an algorithm, TRAM, to navigate the space/time/data/risk tradeoff in practice. In particular, we show that for a fixed risk (or data size), as the data size increases (resp. risk increases) the running time of TRAM decreases. Our extensive experiments on real data sets demonstrate the existence and practical utility of such tradeoffs, not only for k-means but also for Gaussian Mixture Models.

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。

↑