Quantum-Inspired Unitary Pooling for Multispectral Satellite Image Classification

• URL: http://arxiv.org/abs/2603.15522v1
• Date: Mon, 16 Mar 2026 16:47:43 GMT
• Title: Quantum-Inspired Unitary Pooling for Multispectral Satellite Image Classification
• Abstract summary: We show that unitary evolutions and Hilbert-space embeddings can introduce useful inductive biases for learning.<n>We introduce a fully classical pooling mechanism that maps latent features to complex projective space via a fixed-reference unitary action.<n> Empirical results on multispectral satellite imagery show that incorporating this quantum-inspired pooling operation into a convolutional neural network improves stability, accelerates convergence, and substantially reduces variance compared to standard pooling baselines.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multispectral satellite imagery poses significant challenges for deep learning models due to the high dimensionality of spectral data and the presence of structured correlations across channels. Recent work in quantum machine learning suggests that unitary evolutions and Hilbert-space embeddings can introduce useful inductive biases for learning. In this work, we show that several empirical advantages often attributed to quantum feature maps can be more precisely understood as consequences of geometric structure induced by unitary group actions and the associated quotient symmetries. Motivated by this observation, we introduce a fully classical pooling mechanism that maps latent features to complex projective space via a fixed-reference unitary action. This construction effectively collapses non-identifiable degrees of freedom, leading to a reduction in the dimensionality of the learned representations. Empirical results on multispectral satellite imagery show that incorporating this quantum-inspired pooling operation into a convolutional neural network improves optimization stability, accelerates convergence, and substantially reduces variance compared to standard pooling baselines. These results clarify the role of geometric structure in quantum-inspired architectures and demonstrate that their benefits can be reproduced through principled geometric inductive biases implemented entirely within classical deep learning models.

Related papers

• Neural quantum states in condensed matter: advances, best practices, and prospects [0.0]
  Neural quantum states provide flexible variational representations of quantum many-body wave functions.<n>We discuss the architectures, symmetry constraints, optimization methods, and sampling strategies underlying state-of-the-art calculations.<n>We outline promising directions in which neural quantum states may extend the reach of classical simulations of strongly correlated quantum matter.
  arXiv  Detail & Related papers  (2026-08-21T16:51:31Z)
• Beyond the Expressivity-Trainability Paradox: A Dynamical Lie Algebra Perspective on Navigating Barren Plateaus in Quantum Machine Learning [0.0]
  In Quantum Machine Learning (QML), increasing model capacity typically risks overfitting.<n>This study advances a counter-intuitive paradigm, driven by the "expressivity-trainability paradox"<n>We establish a comprehensive framework linking the algebraic dimension of circuit generators to their optimization dynamics.
  arXiv  Detail & Related papers  (2026-06-30T11:50:52Z)
• Compositional Quantum Heuristics for Max-Clique Detection [0.0]
  In general, circuits that are sufficiently expressive to model complex behaviour often exhibit barren plateaus.<n>In this work we investigate a compositional approach to mitigate this trade-off by assembling larger quantum models from smaller subcomponents.<n>We use this framework to design permutation-equivariant quantum graph neural networks for identifying maximal cliques in graphs.
  arXiv  Detail & Related papers  (2026-05-08T11:38:57Z)
• A Multiplicative Neural Network Architecture: Locality and Regularity of Appriximation [1.7188280334580195]
  We introduce a multiplicative neural network architecture in which multiplicative interactions constitute the fundamental representation.<n>We analyze its approximation properties in terms of locality and regularity in Bessel potential spaces.
  arXiv  Detail & Related papers  (2026-02-06T04:07:50Z)
• Prospects for quantum advantage in machine learning from the representability of functions [0.815557531820863]
  We show how circuit depth and non-Clifford gate count determine whether a model's output leads to efficient classical simulation or surrogation.<n>We argue that this analysis uncovers common pathways to dequantization that underlie many existing simulation methods.
  arXiv  Detail & Related papers  (2025-12-17T18:14:59Z)
• Emergence of global receptive fields capturing multipartite quantum correlations [0.565473932498362]
  In quantum physics, even simple data with a well-defined structure at the wave function level can be characterized by extremely complex correlations.<n>We show that monitoring the neural network weight space while learning quantum statistics allows to develop physical intuition about complex multipartite patterns.<n>Our findings suggest a fresh look at constructing convolutional neural networks for processing data with non-local patterns.
  arXiv  Detail & Related papers  (2024-08-23T12:45:40Z)
• Order-invariant two-photon quantum correlations in PT-symmetric interferometers [62.997667081978825]
  Multiphoton correlations in linear photonic quantum networks are governed by matrix permanents. We show that the overall multiphoton behavior of a network from its individual building blocks typically defies intuition. Our results underline new ways in which quantum correlations may be preserved in counterintuitive ways even in small-scale non-Hermitian networks.
  arXiv  Detail & Related papers  (2023-02-23T09:43:49Z)
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning [52.77024349608834]
  Building a quantum analog of classical deep neural networks represents a fundamental challenge in quantum computing. Key issue is how to address the inherent non-linearity of classical deep learning. We introduce the Quantum Path Kernel, a formulation of quantum machine learning capable of replicating those aspects of deep machine learning.
  arXiv  Detail & Related papers  (2022-12-22T16:06:24Z)
• Decimation technique for open quantum systems: a case study with driven-dissipative bosonic chains [62.997667081978825]
  Unavoidable coupling of quantum systems to external degrees of freedom leads to dissipative (non-unitary) dynamics. We introduce a method to deal with these systems based on the calculation of (dissipative) lattice Green's function. We illustrate the power of this method with several examples of driven-dissipative bosonic chains of increasing complexity.
  arXiv  Detail & Related papers  (2022-02-15T19:00:09Z)
• Exploring complex graphs using three-dimensional quantum walks of correlated photons [52.77024349608834]
  We introduce a new paradigm for the direct experimental realization of excitation dynamics associated with three-dimensional networks. This novel testbed for the experimental exploration of multi-particle quantum walks on complex, highly connected graphs paves the way towards exploiting the applicative potential of fermionic dynamics in integrated quantum photonics.
  arXiv  Detail & Related papers  (2020-07-10T09:15:44Z)
• Lorentz Group Equivariant Neural Network for Particle Physics [58.56031187968692]
  We present a neural network architecture that is fully equivariant with respect to transformations under the Lorentz group. For classification tasks in particle physics, we demonstrate that such an equivariant architecture leads to drastically simpler models that have relatively few learnable parameters.
  arXiv  Detail & Related papers  (2020-06-08T17:54:43Z)
• Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms [67.88675386638043]
  The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. We introduce windowed and non-windowed geometric scattering transforms for graphs based upon a very general class of asymmetric wavelets. We show that these asymmetric graph scattering transforms have many of the same theoretical guarantees as their symmetric counterparts.
  arXiv  Detail & Related papers  (2019-11-14T17:23:06Z)

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.