LegoQ: Density-Matrix Representation Learning with Spectral-Spatial State Transitions for Hyperspectral Classification

• URL: http://arxiv.org/abs/2607.28970v1
• Date: Fri, 31 Jul 2026 02:47:16 GMT
• Title: LegoQ: Density-Matrix Representation Learning with Spectral-Spatial State Transitions for Hyperspectral Classification
• Abstract summary: This paper presents method, a classical density-matrix representation learning framework for hyperspectral images.<n>The spectral bands are divided into groups and each group is mapped to a positive semi-definite, Hermitian, trace-normalized matrix state.<n>A composable stack of spectral, spatial, and inter-group transitions then updates the states while repeatedly projecting them back to the valid state set.<n>The results support constrained matrix-state learning as a practical alternative to vector-only hyperspectral classification without requiring quantum hardware.
• Score: 39.58966970890936
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hyperspectral image classification is complicated by mixed pixels, spectral ambiguity, class imbalance, and limited annotations. Most current classifiers encode a pixel or patch as a deterministic vector and apply a linear or multilayer softmax head. Although effective for discrimination, this representation does not directly expose how mixed or uncertain a sample is. This paper presents \method, a classical density-matrix representation learning framework for hyperspectral images. The spectral bands are divided into groups and each group is mapped to a positive semi-definite, Hermitian, trace-normalized matrix state. A composable stack of spectral, spatial, and inter-group transitions then updates the states while repeatedly projecting them back to the valid state set. Instead of flattening the final features, \method\ aggregates the group states and compares them with learnable class-prototype density matrices through Uhlmann fidelity. The normalized eigenspectrum, von Neumann entropy, purity, and prototype fidelity provide sample-level diagnostics that are unavailable from a conventional vector head. On Indian Pines, ten runs yield an overall accuracy of $96.20\pm0.70\%$, an average accuracy of $95.57\pm1.29\%$, and a kappa coefficient of $95.66\pm0.80\%$. On WHU-Hi-LongKou, the best of ten runs reaches $97.52\%$ overall accuracy. Classification maps and feature projections show that the transition stack produces compact and better separated class structures. The results support constrained matrix-state learning as a practical alternative to vector-only hyperspectral classification without requiring quantum hardware.

Related papers

• Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems [48.096969031315744]
  We show that on systems assembled from weakly interacting components, the component is absent from the model rather than modeled, and no function of it can be predicted at any accuracy.<n>We propose to score instead the $$-algebra the coordinates generate, so that products and powers come free and a component's cost is governed only by its generators.
  arXiv  Detail & Related papers  (2026-08-19T13:49:51Z)
• Near-Optimal Mode Scaling for Finite-Dimensional Boson Sampling via Lie-Algebraic Leakage Bounds [0.8594140167290097]
  Boson sampling on matter-based platforms requires encoding the bosonic modes in finite-dimensional local Hilbert spaces.<n>We develop a unified framework for non-interacting sampling on the irreducible representations of compact Lie groups.<n>We prove, in a Gaussian model of the transition matrix, that its spectral norm concentrates at $tildeO(stn)$ rather than the $O(n)$ worst-case of prior spin-based emulations.
  arXiv  Detail & Related papers  (2026-07-13T15:36:29Z)
• Zeta: Dual Whitening for Matrix Optimization via Coordinate-Adaptive Preconditioning [56.24532075189964]
  We propose Zeta, a dual whitening that applies coordinate whitening and spectral whitening in a strictly ordered pipeline.<n>We prove that Zeta matches or surpasses strong baselines across language modeling (0.6B to 8B parameters), mixture-of-experts architectures, and vision tasks.
  arXiv  Detail & Related papers  (2026-06-12T07:10:17Z)
• SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery [14.526295398233747]
  Generalized Category Discovery (GCD) aims to identify novel categories in unlabeled data while leveraging a small labeled subset of known classes.<n>We propose SpectralGCD, an efficient and effective multimodal approach to GCD that uses CLIP cross-modal image-concept similarities as a unified cross-modal representation.<n>SpectralGCD delivers accuracy comparable to or significantly superior to state-of-the-art methods at a fraction of the computational cost.
  arXiv  Detail & Related papers  (2026-02-19T14:18:50Z)
• Phase-space entropy at acquisition reflects downstream learnability [54.4100065023873]
  We propose an acquisition-level scalar $S_mathcal B$ based on instrument-resolved phase space.<n>We show theoretically that (S_mathcal B) correctly identifies the phase-space coherence of periodic sampling.<n>$|S_mathcal B|$ consistently ranks sampling geometries and predicts downstream reconstruction/recognition difficulty emphwithout training.
  arXiv  Detail & Related papers  (2025-12-22T10:03:51Z)
• Spectral Norm of Convolutional Layers with Circular and Zero Paddings [55.233197272316275]
  We generalize the use of the Gram iteration to zero padding convolutional layers and prove its quadratic convergence. We also provide theorems for bridging the gap between circular and zero padding convolution's spectral norm.
  arXiv  Detail & Related papers  (2024-01-31T23:48:48Z)
• Community Detection in the Hypergraph SBM: Exact Recovery Given the Similarity Matrix [1.74048653626208]
  We study the performance of algorithms which operate on the $similarity$matrix $W$, where $W_ij$ reports the number of hyperedges containing both $i$ and $j$. We design a simple and highly efficient spectral algorithm with nearly linear runtime and show that it achieves the min-bisection threshold.
  arXiv  Detail & Related papers  (2022-08-23T15:22:05Z)
• Regular Polytope Networks [29.44144177954405]
  We argue that a transformation can be fixed with no loss of accuracy and with a reduction in memory usage. It can also be used to learn stationary and maximally separated embeddings. We show that the stationarity of the embedding and its maximal separated representation can be theoretically justified.
  arXiv  Detail & Related papers  (2021-03-29T14:11:32Z)
• Linear-Sample Learning of Low-Rank Distributions [56.59844655107251]
  We show that learning $ktimes k$, rank-$r$, matrices to normalized $L_1$ distance requires $Omega(frackrepsilon2)$ samples. We propose an algorithm that uses $cal O(frackrepsilon2log2fracepsilon)$ samples, a number linear in the high dimension, and nearly linear in the matrices, typically low, rank proofs.
  arXiv  Detail & Related papers  (2020-09-30T19:10:32Z)
• Multiway $p$-spectral graph cuts on Grassmann manifolds [0.3441021278275805]
  We present a novel direct multiway spectral clustering algorithm in the $p$-norm, for $p in (1, 2]$. The problem of computing multiple eigenvectors of the graph $p$-Laplacian is recasted as an unconstrained minimization problem on a Grassmann manifold. Monitoring the monotonic decrease of the balanced graph cuts guarantees that we obtain the best available solution from the $p$-levels considered.
  arXiv  Detail & Related papers  (2020-08-30T16:25:04Z)
• Spectral Learning on Matrices and Tensors [74.88243719463053]
  We show that tensor decomposition can pick up latent effects that are missed by matrix methods. We also outline computational techniques to design efficient tensor decomposition methods.
  arXiv  Detail & Related papers  (2020-04-16T22:53:00Z)

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.