High-Dimensional Tensor Discriminant Analysis: Low-Rank Discriminant Structure, Representation Synergy, and Theoretical Guarantees

• URL: http://arxiv.org/abs/2512.12122v1
• Date: Sat, 13 Dec 2025 01:24:54 GMT
• Title: High-Dimensional Tensor Discriminant Analysis: Low-Rank Discriminant Structure, Representation Synergy, and Theoretical Guarantees
• Authors: Elynn Chen, Yuefeng Han, Jiayu Li,
• Abstract summary: High-dimensional tensor-valued predictors arise in modern applications, increasingly as learned representations from neural networks.<n>Existing tensor classification methods rely on sparsity or Tucker structures and often lack theoretical guarantees.<n>We introduce CP lowrank structure for the discriminant tensor, a modeling perspective not previously explored.<n>We establish global convergence and minimax-optimal misclassification rates.
• Score: 3.6485800000302393
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-dimensional tensor-valued predictors arise in modern applications, increasingly as learned representations from neural networks. Existing tensor classification methods rely on sparsity or Tucker structures and often lack theoretical guarantees. Motivated by empirical evidence that discriminative signals concentrate along a few multilinear components, we introduce CP low-rank structure for the discriminant tensor, a modeling perspective not previously explored. Under a Tensor Gaussian Mixture Model, we propose high-dimensional CP low-rank Tensor Discriminant Analysis (CP-TDA) with Randomized Composite PCA (\textsc{rc-PCA}) initialization, that is essential for handling dependent and anisotropic noise under weaker signal strength and incoherence conditions, followed by iterative refinement algorithm. We establish global convergence and minimax-optimal misclassification rates. To handle tensor data deviating from tensor normality, we develop the first semiparametric tensor discriminant model, in which learned tensor representations are mapped via deep generative models into a latent space tailored for CP-TDA. Misclassification risk decomposes into representation, approximation, and estimation errors. Numerical studies and real data analysis on graph classification demonstrate substantial gains over existing tensor classifiers and state-of-the-art graph neural networks, particularly in high-dimensional, small-sample regimes.

Related papers

• Score-Based Model for Low-Rank Tensor Recovery [49.158601255093416]
  Low-rank tensor decompositions (TDs) provide an effective framework for multiway data analysis.<n>Traditional TD methods rely on predefined structural assumptions, such as CP or Tucker decompositions.<n>We propose a score-based model that eliminates the need for predefined structural or distributional assumptions.
  arXiv  Detail & Related papers  (2025-06-27T15:05:37Z)
• 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)
• Tensor Convolutional Network for Higher-Order Interaction Prediction in Sparse Tensors [74.31355755781343]
  We propose TCN, an accurate and compatible tensor convolutional network that integrates seamlessly with TF methods for predicting top-k interactions.<n>We show that TCN integrated with a TF method outperforms competitors, including TF methods and a hyperedge prediction method.
  arXiv  Detail & Related papers  (2025-03-14T18:22:20Z)
• Statistical Inference for Low-Rank Tensor Models [6.461409103746828]
  This paper introduces a unified framework for inferring general and low-Tucker-rank linear functionals of low-Tucker-rank signal tensors.<n>By leveraging a debiasing strategy and projecting onto the tangent space of the low-Tucker-rank manifold, we enable inference for general and structured linear functionals.
  arXiv  Detail & Related papers  (2025-01-27T17:14:35Z)
• High-Dimensional Tensor Discriminant Analysis with Incomplete Tensors [5.745276598549783]
  We introduce a novel approach to tensor classification with incomplete data, framed within high-dimensional linear discriminant analysis. Our method demonstrates excellent performance in simulations and real data analysis, even with significant proportions of missing data.
  arXiv  Detail & Related papers  (2024-10-18T18:00:16Z)
• A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks [44.31777384413466]
  Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. In this paper, we focus on node-wise classification and explore the feature evolution through the lens of the "Neural Collapse" phenomenon. We show that even an "optimistic" mathematical model requires that the graphs obey a strict structural condition in order to possess a minimizer with exact collapse.
  arXiv  Detail & Related papers  (2023-07-04T23:03:21Z)
• Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements [30.395874385570007]
  A fundamental task is to faithfully recover tensors from highly incomplete measurements. We develop an algorithm to directly recover the tensor factors in the Tucker decomposition. We show that it provably converges at a linear independent rate of the ground truth tensor for two canonical problems.
  arXiv  Detail & Related papers  (2021-04-29T17:44:49Z)
• Tensor-Train Networks for Learning Predictive Modeling of Multidimensional Data [0.0]
  A promising strategy is based on tensor networks, which have been very successful in physical and chemical applications. We show that the weights of a multidimensional regression model can be learned by means of tensor networks with the aim of performing a powerful compact representation. An algorithm based on alternating least squares has been proposed for approximating the weights in TT-format with a reduction of computational power.
  arXiv  Detail & Related papers  (2021-01-22T16:14:38Z)
• Inference for Low-rank Tensors -- No Need to Debias [22.163281794187544]
  In this paper, we consider the statistical inference for several low-rank tensor models. For the rank-one PCA model, we establish the theory for inference on each individual singular tensor. Finally, simulations are presented to corroborate our theoretical discoveries.
  arXiv  Detail & Related papers  (2020-12-29T16:48:02Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)
• 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)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

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.