• Cite Icon1
  • https://doi.org/10.32604/cmes.2022.021636Copy DOI Icon

Tensor Train Random Projection

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This work proposes a Tensor Train Random Projection (TTRP) method for dimension reduction, where pairwise distances can be approximately preserved. Our TTRP is systematically constructed through a Tensor Train (TT) representation with TT-ranks equal to one. Based on the tensor train format, this random projection method can speed up the dimension reduction procedure for high-dimensional datasets and requires fewer storage costs with little loss in accuracy, compared with existing methods. We provide a theoretical analysis of the bias and the variance of TTRP, which shows that this approach is an expected isometric projection with bounded variance, and we show that the scaling Rademacher variable is an optimal choice for generating the corresponding TT-cores. Detailed numerical experiments with synthetic datasets and the MNIST dataset are conducted to demonstrate the efficiency of TTRP.

Loading PDF

Similar Papers
  • Book Chapter

The Random Projection Method for Stiff Multi-species Detonation Computation

  • Jan 01, 2001
  • Weizhu Bao +1
  • Research Article
  • Citations11

A new incremental constraint projection method for solving monotone variational inequalities

  • Aug 11, 2016
  • Optimization Methods and Software
  • F.Q Xia +2
  • Book Chapter
  • Citations12

Solution of the Discrete Ill-Posed Problem on the Basis of Singular Value Decomposition and Random Projection

  • Nov 22, 2017
  • Elena G Revunova
  • Research Article
  • Citations5

High-Order Tensor-Train Finite-Volume Methods for Shallow-Water Equations

  • Aug 01, 2025
  • Monthly Weather Review
  • M Engin Danis +6
  • Conference Article

Investigation of different dimension reduction and normalization methods for local appearance-based face recognition

  • Apr 01, 2009
  • Berkay Topcu +1
  • Conference Article
  • Citations7

Multi-instance Cancelable Biometric System using Convolutional Neural Network

  • Oct 01, 2019
  • Tanuja Sudhakar +1
  • Research Article
  • Citations3

FastMap Projection for High-Dimensional Data: A Cluster Ensemble Approach

  • Dec 31, 2016
  • International Journal of Database Theory and Application
  • Imran Khan +2
  • Research Article
  • Citations4

Low-Rank Tensor Train Dynamic Mode Decomposition: An Enhanced Multivariate Signal Processing Method for Mechanical Fault Diagnosis

  • Jan 01, 2025
  • IEEE Transactions on Instrumentation and Measurement
  • Yongqiang Yin +5
  • Conference Article
  • Citations26

Randomized Tensor Ring Decomposition and Its Application to Large-scale Data Reconstruction

  • Jan 07, 2019
  • Longhao Yuan +3
  • Research Article
  • Citations4

Dimensionality reduction distills complex evolutionary relationships in seasonal influenza and SARS-CoV-2.

  • Nov 14, 2024
  • Virus evolution
  • Sravani Nanduri +3
  • Research Article
  • Citations6

An Incremental Tensor Train Decomposition Algorithm

  • Mar 26, 2024
  • SIAM Journal on Scientific Computing
  • Doruk Aksoy +3
  • Research Article
  • Citations10

Streaming Tensor Train Approximation

  • Oct 04, 2023
  • SIAM Journal on Scientific Computing
  • Daniel Kressner +2
  • Research Article
  • Citations116

Computation of extreme eigenvalues in higher dimensions using block tensor train format

  • Dec 27, 2013
  • Computer Physics Communications
  • S.V Dolgov +3
  • Single Report

WaveTrain: A Python package for numerical quantum mechanics of chain-like systems based on tensor trains

  • Jan 01, 2023
  • TIB Repositorium
  • Riedel, Jerome +3
  • Research Article

Dimensionality Reduction and Machine Learning Methods for COVID-19 Classification Using Chest CT Images

  • Mar 16, 2026
  • Electronics
  • Alexandra Isabella Somodi +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.