我们提供了一个简单的方法和相关的理论分析,有效地估计高阶lp距离。虽然分析主要集中在l4上,但我们的方法自然延伸到p = 6,8,10.. (i.e.,当p为偶数时)。基于距离的方法在机器学习中很流行。在大规模应用中,存储、计算和检索距离可能在空间和时间上都是不允许的。如果0 < p <= 2,则存在用于估计lp距离的有效算法。p > 2的任务是困难的。我们的工作部分填补了这一空白。
英文摘要:
We provide a simple method and relevant theoretical analysis for efficiently estimating higher-order lp distances. While the analysis mainly focuses on l4, our methodology extends naturally to p = 6,8,10..., (i.e., when p is even). Distance-based methods are popular in machine learning. In large-scale applications, storing, computing, and retrieving the distances can be both space and time prohibitive. Efficient algorithms exist for estimating lp distances if 0 < p <= 2. The task for p > 2 is known to be difficult. Our work partially fills this gap.
Random Projections through multiple optical scattering: Approximating kernels at the speed of light
Laboratoire de Physique Statistique, CNRS UMR 8550 & École Normale Supérieure(统计物理实验室,CNRS UMR 8550 & 巴黎高等师范学院);Institut Langevin, ESPCI and CNRS UMR 7587(朗之万研究所,ESPCI 与 CNRS UMR 7587);Paris Diderot University, Sorbonne Paris Cité(巴黎狄德罗大学,索邦巴黎西岱);ENSTA Bretagne and Lab-STICC UMR 6285(ENSTA 布列塔尼与 Lab-STICC UMR 6285);Laboratoire Kastler Brossel, CNRS UMR 8552 & École Normale Supérieure(卡斯特勒-布罗塞尔实验室,CNRS UMR 8552 & 巴黎高等师范学院);Sorbonne Universités, Université Pierre et Marie Curie Paris 06(索邦大学群,皮埃尔和玛丽·居里大学(巴黎第六大学));PSL Research University(巴黎文理研究大学)
Hilbert Curve Projection Distance for Distribution Comparison
Institute of Statistics and Big Data, Renmin University of China(中国人民大学统计与大数据研究院);Center for Applied Statistics, Institute of Statistics and Big Data, Renmin University of China(中国人民大学统计与大数据研究院应用统计中心);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);School of Mathematics and Statistics, Beijing Institute of Technology(北京理工大学数学与统计学院)