Out-of-distribution generalization for learning quantum dynamics

Abstract

Generalization bounds are a critical tool to assess the training data requirements of Quantum Machine Learning (QML). Recent work has established guarantees for in-distribution generalization of quantum neural networks (QNNs), where training and testing data are drawn from the same data distribution. However, there are currently no results on out-of-distribution generalization in QML, where we require a trained model to perform well even on data drawn from a different distribution to the training distribution. Here, we prove out-of-distribution generalization for the task of learning an unknown unitary. In particular, we show that one can learn the action of a unitary on entangled states having trained only product states. Since product states can be prepared using only single-qubit gates, this advances the prospects of learning quantum dynamics on near term quantum hardware, and further opens up new methods for both the classical and quantum compilation of quantum circuits.

8 pages (main body) + 18 pages (references and appendix); 4+2 figures; V3 includes additional explanations and numerical experiments in the appendix

References in corpus (18)

• An introduction to quantum machine learning
• Quantum advantage in learning from experiments
• Generalization in quantum machine learning from few training data
• The randomized measurement toolbox
• Information-theoretic bounds on quantum advantage in machine learning
• Provably efficient machine learning for quantum many-body problems
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Efficient measure for the expressivity of variational quantum algorithms
• Quantum Algorithmic Measurement
• Classical Shadow Tomography with Locally Scrambled Quantum Dynamics
• Minimal Model for Fast Scrambling
• On the statistical complexity of quantum circuits
• Quantum advantages for Pauli channel estimation
• Quantum phase detection generalisation from marginal quantum neural network models
• Towards a Theoretical Framework of Out-of-Distribution Generalization
• Structural risk minimization for quantum linear classifiers
• Pauli error estimation via Population Recovery
• Experimental Quantum Learning of a Spectral Decomposition

Cited by in corpus (42)

• Challenges and Opportunities in Quantum Machine Learning
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Understanding quantum machine learning also requires rethinking generalization
• Generative quantum machine learning via denoising diffusion probabilistic models
• Trainability barriers and opportunities in quantum generative modeling
• Dynamical simulation via quantum machine learning with provable generalization
• Learning quantum states and unitaries of bounded gate complexity
• Variational quantum simulation: a case study for understanding warm starts
• Learning Quantum Processes and Hamiltonians via the Pauli Transfer Matrix
• Learning shallow quantum circuits
• Classically estimating observables of noiseless quantum circuits
• Complexity of quantum circuits via sensitivity, magic, and coherence
• Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
• Lie-algebraic classical simulations for quantum computing
• Transition Role of Entangled Data in Quantum Machine Learning
• Mitigated barren plateaus in the time-nonlocal optimization of analog quantum-algorithm protocols
• Quantum Next Generation Reservoir Computing: An Efficient Quantum Algorithm for Forecasting Quantum Dynamics
• Opportunities and challenges of quantum computing for climate modelling
• Generalization Error Bound for Quantum Machine Learning in NISQ Era -- A Survey
• Quantum reservoir computing for photonic entanglement witnessing
• The power and limitations of learning quantum dynamics incoherently
• Simulating quantum circuits with arbitrary local noise using Pauli Propagation
• Quantum Tensor Product Decomposition from Choi State Tomography
• Quantum neural compressive sensing for ghost imaging
• Dual-Capability Machine Learning Models for Quantum Hamiltonian Parameter Estimation and Dynamics Prediction
• Harnessing Quantum Support Vector Machines for Cross-Domain Classification of Quantum States
• Parallel-in-time quantum simulation via Page and Wootters quantum time
• High-fidelity dimer excitations using quantum hardware
• Deep Circuit Compression for Quantum Dynamics via Tensor Networks
• Measurement-based quantum machine learning
• Learning unitaries with quantum statistical queries
• Learning Fourier series with parametrized quantum circuits
• Data-Dependent Generalization Bounds for Parameterized Quantum Models Under Noise
• Out-of-distribution generalisation for learning quantum channels with low-energy coherent states
• Deep Neural Network-assisted improvement of quantum compressed sensing tomography
• Nearly query-optimal classical shadow estimation of unitary channels
• Multi-target quantum compilation algorithm
• Quantum-enhanced learning with a controllable bosonic variational sensor network
• Direct Gradient Computation for Barren Plateaus in Parameterized Quantum Circuits
• Measuring Incompatible Observables with Quantum Neural Networks
• Disentangling quantum autoencoder
• Quantum generative classification with mixed states