层次模型:高维中的内在可分性
Hierarchical Models: Intrinsic Separability in High Dimensions
摘要:
人们早就注意到,高维数据表现出奇怪的模式。这被不同地解释为“祝福”或“诅咒”,导致文献中令人不安的不一致。我们认为,这些模式产生于一个内在的层次生成过程。对过程建模会创建一个约束网络,协调许多不同的理论和结果。该模型还意味着高维数据具有先天的可分性,可用于机器学习。我们演示了如何允许数学定义的开集学习问题,导致性能的定性和定量的改善。
英文摘要:
It has long been noticed that high dimension data exhibits strange patterns. This has been variously interpreted as either a "blessing" or a "curse", causing uncomfortable inconsistencies in the literature. We propose that these patterns arise from an intrinsically hierarchical generative process. Modeling the process creates a web of constraints that reconcile many different theories and results. The model also implies high dimensional data posses an innate separability that can be exploited for machine learning. We demonstrate how this permits the open-set learning problem to be defined mathematically, leading to qualitative and quantitative improvements in performance.
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。