Quantum feature-map learning with reduced resource overhead

Abstract

Current quantum computers require algorithms that use limited resources economically. In quantum machine learning, success hinges on quantum feature-maps, which embed classical data into the state space of qubits. We introduce Quantum Feature-Map Learning via Analytic Iterative Reconstructions (Q-FLAIR), an algorithm that reduces quantum resource overhead in iterative feature-map circuit construction. It shifts workloads to a classical computer via partial analytic reconstructions of the quantum model, using only a few evaluations. For each probed gate addition to the ansatz, the simultaneous selection and optimization of the data feature and weight parameter is then entirely classical. Integrated into quantum neural network and quantum kernel support vector classifiers, Q-FLAIR shows state-of-the-art benchmark performance. Since resource overhead decouples from feature dimension, we train a quantum model on a real IBM device in only four hours, surpassing 90% accuracy on the full-resolution MNIST dataset (784 features, digits 3 vs 5). Such results were previously unattainable, as the feature dimension prohibitively drives hardware demands for fixed and search costs for adaptive ansätze. Furthermore, Q-FLAIR demonstrates de-quantization robustness against direct classical modeling, satisfying a benchmark rare in the literature and a necessary condition for potential quantum advantage. By rethinking feature-map learning beyond black-box optimization, this work takes a concrete step toward enabling quantum machine learning for real-world problems and near-term quantum computers.

24 pages, 12 figures, 2 tables

References in corpus (47)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Evaluating analytic gradients on quantum hardware
• An adaptive variational algorithm for exact molecular simulations on a quantum computer
• Circuit-centric quantum classifiers
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Power of data in quantum machine learning
• Challenges and Opportunities in Quantum Machine Learning
• Data re-uploading for a universal quantum classifier
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• A rigorous and robust quantum speed-up in supervised machine learning
• Layerwise learning for quantum neural networks
• Hybrid Quantum-Classical Approach to Quantum Optimal Control
• Barren Plateaus in Variational Quantum Computing
• Structure optimization for parameterized quantum circuits
• Quantum circuit architecture search for variational quantum algorithms
• Sequential minimal optimization for quantum-classical hybrid algorithms
• Demonstration of quantum advantage in machine learning
• Quantum machine learning for image classification
• Training Quantum Embedding Kernels on Near-Term Quantum Computers
• Fisher Information in Noisy Intermediate-Scale Quantum Applications
• Mixed Quantum-Classical Method For Fraud Detection with Quantum Feature Selection
• Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines
• Quantum Machine Learning for Particle Physics using a Variational Quantum Classifier
• ADAPT-VQE is insensitive to rough parameter landscapes and barren plateaus
• Automatic design of quantum feature maps
• Feature Selection on Quantum Computers
• Event Classification with Quantum Machine Learning in High-Energy Physics
• Quantum classification of the MNIST dataset with Slow Feature Analysis
• Classical surrogates for quantum learning models
• Realizing a quantum generative adversarial network using a programmable superconducting processor
• Quantum Kernel Methods for Solving Differential Equations
• Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
• Machine learning on quantum experimental data toward solving quantum many-body problems
• Trainability and Expressivity of Hamming-Weight Preserving Quantum Circuits for Machine Learning
• Hybrid Genetic Optimisation for Quantum Feature Map Design
• Quantum Hamiltonian Embedding of Images for Data Reuploading Classifiers
• Fast gradient-free optimization of excitations in variational quantum eigensolvers
• Greedy Gradient-free Adaptive Variational Quantum Algorithms on a Noisy Intermediate Scale Quantum Computer
• Classification and reconstruction for single-pixel imaging with classical and quantum neural networks
• Application of Quantum Pre-Processing Filter for Binary Image Classification with Small Samples
• On the Differential Topology of Expressivity of Parameterized Quantum Circuits
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits