Exponential data encoding for quantum supervised learning

Abstract

Reliable quantum supervised learning of a multivariate function mapping depends on the expressivity of the corresponding quantum circuit and measurement resources. We introduce exponential-data-encoding strategies that are hardware-efficient and optimal amongst all non-entangling Pauli-encoded schemes, which is sufficient for a quantum circuit to express general functions having very broad Fourier frequency spectra using only exponentially few encoding gates. We show that such an encoding strategy not only reduces the quantum resources, but also exhibits practical resource advantage during training in contrast with known efficient classical strategies when polynomial-depth training circuits are also employed. When computation resources are constrained, we numerically demonstrate that even exponential-data-encoding circuits with single-layer training modules can generally express functions that lie outside the classically-expressible region, thereby supporting the practical benefits of such a resource advantage. Finally, we illustrate the performance of exponential encoding in learning the potential-energy surface of the ethanol molecule and California's housing prices

21 pages, 13 figures

References in corpus (15)

• Variational Quantum Algorithms
• Noisy intermediate-scale quantum (NISQ) algorithms
• An introduction to quantum machine learning
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Hybrid quantum-classical algorithms and quantum error mitigation
• Quantum-enhanced machine learning
• Artificial Intelligence and Statistics
• Information-theoretic bounds on quantum advantage in machine learning
• Effect of barren plateaus on gradient-free optimization
• Is quantum advantage the right goal for quantum machine learning?
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Efficient measure for the expressivity of variational quantum algorithms
• Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces
• Single-qubit universal classifier implemented on an ion-trap quantum device

Cited by in corpus (13)

• Generalization despite overfitting in quantum machine learning models
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Multidimensional Fourier series with quantum circuits
• On fundamental aspects of quantum extreme learning machines
• Dequantizing quantum machine learning models using tensor networks
• An exponentially-growing family of universal quantum circuits
• Constrained and Vanishing Expressivity of Quantum Fourier Models
• Virtual distillation with noise dilution
• Gradients and frequency profiles of quantum re-uploading models
• Expressivity of deterministic quantum computation with one qubit
• Robustness of optimized numerical estimation schemes for noisy variational quantum algorithms
• When Quantum and Classical Models Disagree: Learning Beyond Minimum Norm Least Square
• Quantum Deep Sets and Sequences