Quantum embeddings for machine learning

Abstract

Quantum classifiers are trainable quantum circuits used as machine learning models. The first part of the circuit implements a quantum feature map that encodes classical inputs into quantum states, embedding the data in a high-dimensional Hilbert space; the second part of the circuit executes a quantum measurement interpreted as the output of the model. Usually, the measurement is trained to distinguish quantum-embedded data. We propose to instead train the first part of the circuit -- the embedding -- with the objective of maximally separating data classes in Hilbert space, a strategy we call quantum metric learning. As a result, the measurement minimizing a linear classification loss is already known and depends on the metric used: for embeddings separating data using the l1 or trace distance, this is the Helstrom measurement, while for the l2 or Hilbert-Schmidt distance, it is a simple overlap measurement. This approach provides a powerful analytic framework for quantum machine learning and eliminates a major component in current models, freeing up more precious resources to best leverage the capabilities of near-term quantum information processors.

11 pages, 6 figures; tutorial available at https://pennylane.ai/qml/app/tutorial_embeddings_metric_learning.html [Version 2 contains minor update]

Cited by in corpus (27)

• The effect of data encoding on the expressive power of variational quantum machine learning models
• Robust data encodings for quantum classifiers
• Quantum machine learning beyond kernel methods
• QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
• Supervised quantum machine learning models are kernel methods
• Qibo: a framework for quantum simulation with hardware acceleration
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Biology and medicine in the landscape of quantum advantages
• Quantum Embedding Search for Quantum Machine Learning
• Quantum Architecture Search via Deep Reinforcement Learning
• Quantum Reinforcement Learning: the Maze problem
• End-to-End Quantum Machine Learning Implemented with Controlled Quantum Dynamics
• Fock State-enhanced Expressivity of Quantum Machine Learning Models
• Entangled Datasets for Quantum Machine Learning
• Hybrid Quantum-Classical Graph Convolutional Network
• Quantum advantage for differential equation analysis
• Evaluating the Performance of Some Local Optimizers for Variational Quantum Classifiers
• QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks
• Performance of Particle Tracking Using a Quantum Graph Neural Network
• The dilemma of quantum neural networks
• Quantum Support Vector Machines for Continuum Suppression in B Meson Decays
• Hybrid Classical-Quantum method for Diabetic Foot Ulcer Classification
• Trainable Discrete Feature Embeddings for Variational Quantum Classifier
• A Unified Framework for Quantum Supervised Learning
• Generalization Study of Quantum Neural Network
• Laplacian Eigenmaps with variational circuits: a quantum embedding of graph data
• K-sparse Pure State Tomography with Phase Estimation