论文标题
分层模型：高维度的内在可分离性
Hierarchical Models: Intrinsic Separability in High Dimensions
论文作者
论文摘要
长期以来，高维数据表现出奇怪的模式。这已被各种解释为“祝福”或“诅咒”，在文献中引起了不舒服的矛盾。我们建议这些模式来自本质上的层次生成过程。对该过程进行建模会创建一个约束的网络，以调和许多不同的理论和结果。该模型还意味着高维数据具有可以利用用于机器学习的先天可分离性。我们演示了这如何允许数学定义开放设定的学习问题，从而导致性能的定性和定量改进。
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.
