A Matched Spectral Benchmark of Quantum Inspired Feature Maps

• URL: http://arxiv.org/abs/2605.24324v1
• Date: Sat, 23 May 2026 01:05:21 GMT
• Title: A Matched Spectral Benchmark of Quantum Inspired Feature Maps
• Abstract summary: Amplitude, angle, and basis encoding are evaluated as deterministic feature maps for classical supervised learning.<n>We show that amplitude encoding can remove information through unit-sphere normalization, angle encoding can become geometrically redundant with raw linear features, and basis encoding can impose a binary Hamming geometry that is poorly aligned with smooth decision structure.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Quantum machine learning is often motivated by the idea that quantum systems can expose useful high-dimensional structure that is difficult to access with classical models. We isolate one central component of this claim: the fixed data-encoding map. Amplitude, angle, and basis encoding are evaluated as deterministic feature maps for classical supervised learning under matched output dimensionality and strong classical controls. The benchmark compares these encodings against raw linear models, random Fourier features, polynomial features, PCA, RBF SVMs, and shallow neural networks across diverse classical datasets. Rather than treating performance as a single endpoint, we analyze the geometry of each representation through effective rank, condition number, centered kernel alignment, predictive performance, and practical overhead. The resulting picture is mechanistic: amplitude encoding can remove magnitude information through unit-sphere normalization, angle encoding can become geometrically redundant with raw linear features, and basis encoding can impose a binary Hamming geometry that is poorly aligned with smooth decision structure. These findings do not argue against quantum computation, however, they show that fixed quantum-inspired encoding geometry alone is not a reliable source of machine-learning advantage on classical data.

Related papers

• Discovering Data Encoding Strategies for Quantum-Classical Neural Networks Using Monte Carlo Tree Search [0.9558392439655014]
  Quantum machine learning (QML) has attracted considerable research interest, yet whether it offers practical benefits over classical approaches remains an open question.<n>We employ Monte Carlo Tree Search (MCTS) to discover optimal data encoding circuits for a quantum-classical convolutional neural network (QCCNN)<n>Our findings provide both a practical method for encoding discovery and new insights into what makes data encodings effective in QML.
  arXiv  Detail & Related papers  (2026-05-18T15:21:42Z)
• Quantum LEGO Learning: A Modular Design Principle for Hybrid Artificial Intelligence [63.39968536637762]
  We introduce Quantum LEGO Learning, a learning framework that treats classical and quantum components as reusable, composable learning blocks.<n>Within this framework, a pre-trained classical neural network serves as a frozen feature block, while a VQC acts as a trainable adaptive module.<n>We develop a block-wise generalization theory that decomposes learning error into approximation and estimation components.
  arXiv  Detail & Related papers  (2026-01-29T14:29:21Z)
• A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding [12.998419492098462]
  Topological stabilizer codes are particularly appealing due to their geometric locality and practical relevance.<n>We propose QuantumSMoE, a quantum vision transformer based decoder that incorporates code structure through plus shaped embeddings.<n> Experiments on the toric code demonstrate that QuantumSMoE outperforms state-of-the-art machine learning decoders.
  arXiv  Detail & Related papers  (2026-01-18T16:49:59Z)
• Fidelity-Preserving Quantum Encoding for Quantum Neural Networks [2.9621136443259872]
  Existing encoding schemes discard spatial and semantic information when adapting high-dimensional images to the limited qubits of Noisy Intermediate-Scale QuantumNISQ devices.<n>We propose a Fidelity-Preserving Quantum Preserving framework that performs near lossless data compression and quantum encoding.<n> Experimental results show that FPQE performs comparably to conventional methods on simple datasets such as MNIST, while achieving clear improvements on more complex ones.
  arXiv  Detail & Related papers  (2025-11-19T11:44:39Z)
• An Efficient Quantum Classifier Based on Hamiltonian Representations [50.467930253994155]
  Quantum machine learning (QML) is a discipline that seeks to transfer the advantages of quantum computing to data-driven tasks.<n>We propose an efficient approach that circumvents the costs associated with data encoding by mapping inputs to a finite set of Pauli strings.<n>We evaluate our approach on text and image classification tasks, against well-established classical and quantum models.
  arXiv  Detail & Related papers  (2025-04-13T11:49:53Z)
• Quantum Data Encoding and Variational Algorithms: A Framework for Hybrid Quantum Classical Machine Learning [0.0]
  Quantum Machine Learning (QML) integrates the calculational framework of quantum mechanics with the adaptive properties of classical machine learning.<n>This article suggests a broad architecture that allows the connection between classical data pipelines and quantum algorithms.
  arXiv  Detail & Related papers  (2025-02-17T16:04:04Z)
• Hybrid Quantum-Classical Machine Learning with String Diagrams [49.1574468325115]
  This paper develops a formal framework for describing hybrid algorithms in terms of string diagrams. A notable feature of our string diagrams is the use of functor boxes, which correspond to a quantum-classical interfaces.
  arXiv  Detail & Related papers  (2024-07-04T06:37:16Z)
• Exponential Quantum Communication Advantage in Distributed Inference and Learning [19.827903766111987]
  We present a framework for distributed computation over a quantum network. We show that for models within this framework, inference and training using gradient descent can be performed with exponentially less communication. We also show that models in this class can encode highly nonlinear features of their inputs, and their expressivity increases exponentially with model depth.
  arXiv  Detail & Related papers  (2023-10-11T02:19:50Z)
• The END: An Equivariant Neural Decoder for Quantum Error Correction [73.4384623973809]
  We introduce a data efficient neural decoder that exploits the symmetries of the problem. We propose a novel equivariant architecture that achieves state of the art accuracy compared to previous neural decoders.
  arXiv  Detail & Related papers  (2023-04-14T19:46:39Z)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• Understanding the Mapping of Encode Data Through An Implementation of Quantum Topological Analysis [0.7106986689736827]
  We show the difference in encoding techniques can be visualized by investigating the topology of the data embedded in complex Hilbert space. Our results suggest the encoding method needs to be considered carefully within different quantum machine learning models.
  arXiv  Detail & Related papers  (2022-09-21T18:46:08Z)
• Towards Quantum Graph Neural Networks: An Ego-Graph Learning Approach [47.19265172105025]
  We propose a novel hybrid quantum-classical algorithm for graph-structured data, which we refer to as the Ego-graph based Quantum Graph Neural Network (egoQGNN) egoQGNN implements the GNN theoretical framework using the tensor product and unity matrix representation, which greatly reduces the number of model parameters required. The architecture is based on a novel mapping from real-world data to Hilbert space.
  arXiv  Detail & Related papers  (2022-01-13T16:35:45Z)
• Quantum Machine Learning with SQUID [64.53556573827525]
  We present the Scaled QUantum IDentifier (SQUID), an open-source framework for exploring hybrid Quantum-Classical algorithms for classification problems. We provide examples of using SQUID in a standard binary classification problem from the popular MNIST dataset.
  arXiv  Detail & Related papers  (2021-04-30T21:34:11Z)

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.