Normalized tensor train decomposition

• URL: http://arxiv.org/abs/2511.04369v1
• Date: Thu, 06 Nov 2025 13:55:33 GMT
• Title: Normalized tensor train decomposition
• Abstract summary: We introduce the normalized tensor train (NTT) decomposition, which aims to approximate a tensor by unit-norm tensors in tensor train format.<n>The low-rank structure of NTT decomposition not only saves storage and computational cost but also preserves the underlying unit-norm structure.<n>We propose NTT-based methods for low-rank tensor recovery, high-dimensional eigenvalue problem, estimation of stabilizer rank, and calculation of the minimum output R'enyi 2-entropy of quantum channels.
• Score: 9.771283737093086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tensors with unit Frobenius norm are fundamental objects in many fields, including scientific computing and quantum physics, which are able to represent normalized eigenvectors and pure quantum states. While the tensor train decomposition provides a powerful low-rank format for tackling high-dimensional problems, it does not intrinsically enforce the unit-norm constraint. To address this, we introduce the normalized tensor train (NTT) decomposition, which aims to approximate a tensor by unit-norm tensors in tensor train format. The low-rank structure of NTT decomposition not only saves storage and computational cost but also preserves the underlying unit-norm structure. We prove that the set of fixed-rank NTT tensors forms a smooth manifold, and the corresponding Riemannian geometry is derived, paving the way for geometric methods. We propose NTT-based methods for low-rank tensor recovery, high-dimensional eigenvalue problem, estimation of stabilizer rank, and calculation of the minimum output R\'enyi 2-entropy of quantum channels. Numerical experiments demonstrate the superior efficiency and scalability of the proposed NTT-based methods.

Related papers

• Pre-Trained Low-Rank Tensor Decomposition for Multi-Dimensional Image Recovery [66.1915813483319]
  We propose the first pre-trained low-rank tensor decomposition framework.<n>It organically integrates the pre-trained large vision model into the classical tensor decomposition framework.<n>It achieves higher recovery fidelity, fewer learnable parameters, and smaller carbon footprint.
  arXiv  Detail & Related papers  (2026-09-11T13:36:36Z)
• Low-Rank Tensor Completion Based on Fractional Regularization with Ky Fan p-k Norm [63.91066367247722]
  This paper addresses low-rank tensor completion (LRTC)<n>It proposes a novel non surrogate, namely the ratio of the tub tensor norm to the tensor Ky Fan p-k norm (TNK)
  arXiv  Detail & Related papers  (2026-06-17T13:12:07Z)
• Normalized Iterative Hard Thresholding for Tensor Recovery [7.5277782201584085]
  Low-rank recovery builds upon ideas from the theory of compressive sensing.<n>We propose a tensor extension of NIHT, referred to as TNIHT, for the recovery of low-rank tensors.
  arXiv  Detail & Related papers  (2025-07-06T03:36:50Z)
• Low-Rank Tensor Recovery via Variational Schatten-p Quasi-Norm and Jacobian Regularization [49.85875869048434]
  We propose a CP-based low-rank tensor function parameterized by neural networks for implicit neural representation.<n>To achieve sparser CP decomposition, we introduce a variational Schatten-p quasi-norm to prune redundant rank-1 components.<n>For smoothness, we propose a regularization term based on the spectral norm of the Jacobian and Hutchinson's trace estimator.
  arXiv  Detail & Related papers  (2025-06-27T11:23:10Z)
• MNT-TNN: Spatiotemporal Traffic Data Imputation via Compact Multimode Nonlinear Transform-based Tensor Nuclear Norm [45.59831141171801]
  Modern communication technologies have introduced new challenges in missing value imputation.<n>We propose a novel imputation method based on a Multimode Transformed Nuclear Norm (MNSS-TNN)<n>We also suggest an Augmented Transform-based Nuclear Norm Families (ATTNNs) framework to enhance the imputation results.
  arXiv  Detail & Related papers  (2025-03-29T02:58:31Z)
• TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training [91.8932638236073]
  We introduce textbfTensorGRaD, a novel method that directly addresses the memory challenges associated with large-structured weights.<n>We show that sparseGRaD reduces total memory usage by over $50%$ while maintaining and sometimes even improving accuracy.
  arXiv  Detail & Related papers  (2025-01-04T20:51:51Z)
• Low-Rank Tensor Learning by Generalized Nonconvex Regularization [25.115066273660478]
  We study the problem of low-rank tensor learning, where only a few samples are observed the underlying tensor. A family of non tensor learning functions are employed to characterize the low-rankness of the underlying tensor. An algorithm designed to solve the resulting majorization-minimization is proposed.
  arXiv  Detail & Related papers  (2024-10-24T03:33:20Z)
• On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee [21.818773423324235]
  This paper focuses on two model compression techniques: low-rank approximation and weight approximation. In this paper, a holistic framework is proposed for model compression from a novel perspective of non optimization.
  arXiv  Detail & Related papers  (2023-03-13T02:14:42Z)
• Multi-Tensor Network Representation for High-Order Tensor Completion [25.759851542474447]
  This work studies the problem of high-dimensional data (referred to tensors) completion from partially observed samplings. We consider that a tensor is a superposition of multiple low-rank components. In this paper, we propose a fundamental tensor decomposition framework: Multi-Tensor Network decomposition (MTNR)
  arXiv  Detail & Related papers  (2021-09-09T03:50:19Z)
• Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification [69.26747803963907]
  Rank-R Feedforward Neural Network (FNN) is a tensor-based nonlinear learning model that imposes Canonical/Polyadic decomposition on its parameters. First, it handles inputs as multilinear arrays, bypassing the need for vectorization, and can thus fully exploit the structural information along every data dimension. We establish the universal approximation and learnability properties of Rank-R FNN, and we validate its performance on real-world hyperspectral datasets.
  arXiv  Detail & Related papers  (2021-04-11T16:37:32Z)
• Spectral Tensor Train Parameterization of Deep Learning Layers [136.4761580842396]
  We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. We show the effects of neural network compression in the classification setting and both compression and improved stability training in the generative adversarial training setting.
  arXiv  Detail & Related papers  (2021-03-07T00:15:44Z)
• Robust Tensor Principal Component Analysis: Exact Recovery via Deterministic Model [5.414544833902815]
  This paper proposes a new method to analyze Robust tensor principal component analysis (RTPCA) It is based on the recently developed tensor-tensor product and tensor singular value decomposition (t-SVD)
  arXiv  Detail & Related papers  (2020-08-05T16:26:10Z)
• T-Basis: a Compact Representation for Neural Networks [89.86997385827055]
  We introduce T-Basis, a concept for a compact representation of a set of tensors, each of an arbitrary shape, which is often seen in Neural Networks. We evaluate the proposed approach on the task of neural network compression and demonstrate that it reaches high compression rates at acceptable performance drops.
  arXiv  Detail & Related papers  (2020-07-13T19:03:22Z)
• Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation [105.33409035876691]
  This paper explores the problem of multi-view spectral clustering (MVSC) based on tensor low-rank modeling. We design a novel structured tensor low-rank norm tailored to MVSC. We show that the proposed method outperforms state-of-the-art methods to a significant extent.
  arXiv  Detail & Related papers  (2020-04-30T11:52:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.