Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric

Abstract

Generalization is the ability of machine learning models to make accurate predictions on new data by learning from training data. However, understanding generalization of quantum machine learning models has been a major challenge. Here, we introduce the data quantum Fisher information metric (DQFIM). It describes the capacity of variational quantum algorithms depending on variational ansatz, training data and their symmetries. We apply the DQFIM to quantify circuit parameters and training data needed to successfully train and generalize. Using the dynamical Lie algebra, we explain how to generalize using a low number of training states. Counter-intuitively, breaking symmetries of the training data can help to improve generalization. Finally, we find that out-of-distribution generalization, where training and testing data are drawn from different data distributions, can be better than using the same distribution. Our work provides a useful framework to explore the power of quantum machine learning models.

26 pages, 18 figures

References in corpus (57)

• Quantum Machine Learning
• Variational Quantum Algorithms
• QuTiP: An open-source Python framework for the dynamics of open quantum systems
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Circuit-centric quantum classifiers
• Quantum Fisher information matrix and multiparameter estimation
• Efficient variational quantum simulator incorporating active error minimisation
• Data re-uploading for a universal quantum classifier
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum autoencoders for efficient compression of quantum data
• Generalization in quantum machine learning from few training data
• Quantum Natural Gradient
• Theory of variational quantum simulation
• Quantum-assisted quantum compiling
• Reinforcement Learning in Different Phases of Quantum Control
• Subspace-search variational quantum eigensolver for excited states
• Provably efficient machine learning for quantum many-body problems
• Variational Fast Forwarding for Quantum Simulation Beyond the Coherence Time
• Quantum machine learning beyond kernel methods
• Exploiting symmetry in variational quantum machine learning
• Theory of overparametrization in quantum neural networks
• Quantum Control Landscapes
• Group-Invariant Quantum Machine Learning
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Linear growth of quantum circuit complexity
• Learning Quantum Systems
• Estimating the gradient and higher-order derivatives on quantum hardware
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Optimal quantum learning of a unitary transformation
• Fisher Information in Noisy Intermediate-Scale Quantum Applications
• Theory for Equivariant Quantum Neural Networks
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Towards provably efficient quantum algorithms for large-scale machine-learning models
• Understanding quantum machine learning also requires rethinking generalization
• Out-of-distribution generalization for learning quantum dynamics
• Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
• Fixed Depth Hamiltonian Simulation via Cartan Decomposition
• On the statistical complexity of quantum circuits
• Quantum machine learning of large datasets using randomized measurements
• Generalization despite overfitting in quantum machine learning models
• Building spatial symmetries into parameterized quantum circuits for faster training
• Speeding up Learning Quantum States through Group Equivariant Convolutional Quantum Ansätze
• Universal Effectiveness of High-Depth Circuits in Variational Eigenproblems
• Abrupt Transitions in Variational Quantum Circuit Training
• Algebraic Compression of Quantum Circuits for Hamiltonian Evolution
• Variational quantum process tomography
• Dynamical simulation via quantum machine learning with provable generalization
• Pseudo-dimension of quantum circuits
• Efficient classical algorithms for simulating symmetric quantum systems
• Quantum Mixed State Compiling
• Retrieving information from a black hole using quantum machine learning
• Effects of noise on the overparametrization of quantum neural networks
• Optimal quantum dataset for learning a unitary transformation
• Effects of quantum resources on the statistical complexity of quantum circuits
• Quantum Energy Landscape and VQA Optimization

Cited by in corpus (10)

• Quantum complexity in gravity, quantum field theory, and quantum information science
• Random Natural Gradient
• Data-Dependent Generalization Bounds for Parameterized Quantum Models Under Noise
• Learning Fourier series with parametrized quantum circuits
• Quantum Curriculum Learning
• Superiority of Krylov shadow tomography in estimating quantum Fisher information: From bounds to exactness
• Double descent in quantum kernel methods
• Disentangling quantum autoencoder
• Quantum Machine Learning for Climate Modelling
• Quantum feature-map learning with reduced resource overhead