We propose a sampling-based method for computing the tensor ring (TR) decomposition of a data tensor. The method uses leverage score sampled alternating least squares to fit the TR cores in an iterative fashion. By taking advantage of the special structure of TR tensors, we can efficiently estimate the leverage scores and attain a method which has complexity sublinear in the number of input tensor entries. We provide high-probability relative-error guarantees for the sampled least squares problems. We compare our proposal to existing methods in experiments on both synthetic and real data. Our method achieves substantial speedup -- sometimes two or three orders of magnitude -- over competing methods, while maintaining good accuracy. We also provide an example of how our method can be used for rapid feature extraction.
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);University of Chinese Academy of Sciences(中国科学院大学)
Randomized Tensor Ring Decomposition and Its Application to Large-scale Data Reconstruction
Graduate School of Engineering, Saitama Institute of Technology(埼玉工业大学工程研究生院);RIKEN Center for Advanced Intelligence Project (AIP)(理化学研究所先进智能项目中心);School of Automation, Guangdong University of Technology(广东工业大学自动化学院);School of Computer Science and Technology, Hangzhou Dianzi University(杭州电子科技大学计算机学院)
Rank Minimization on Tensor Ring: A New Paradigm in Scalable Tensor Decomposition and Completion
Graduate School of Engineering, Saitama Institute of Technology, Japan(日本萨它马工学院工程研究生院);Tensor Learning Unit, RIKEN Center for Advanced Intelligence Project (AIP), Japan(日本RIKEN高级智能项目(AIP)张量学习单元);School of Automation, Guangdong University of Technology, China(中国广东技术大学自动化学院);School of Computer Science and Technology, Hangzhou Dianzi University, China(中国杭州电子科技大学计算机科学与技术学院);Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom(英国伦敦帝国理工学院电子与电气工程系)
Higher-dimension Tensor Completion via Low-rank Tensor Ring Decomposition
Graduate School of Engineering, Saitama Institute of Technology, Japan(埼玉工业大学研究生院);Tensor Learning Unit, RIKEN Center for Advanced Intelligence Project (AIP), Japan(RIKEN先进智能项目中心张量学习单元);School of Automation, Guangdong University of Technology, China(广东工业大学自动化学院);School of Computer Science and Technology, Hangzhou Dianzi University, China(杭州电子科技大学计算机科学与技术学院);School of Information Science and Engineering, Shandong University, China(山东大学信息科学与工程学院);Institute of Brain and Brain-Inspired Science, Shandong University, China(山东大学脑与脑智科学研究所)