Enhancing Generative Models via Quantum Correlations

Abstract

Generative modeling using samples drawn from the probability distribution constitutes a powerful approach for unsupervised machine learning. Quantum mechanical systems can produce probability distributions that exhibit quantum correlations which are difficult to capture using classical models. We show theoretically that such quantum correlations provide a powerful resource for generative modeling. In particular, we provide an unconditional proof of separation in expressive power between a class of widely-used generative models, known as Bayesian networks, and its minimal quantum extension. We show that this expressivity advantage is associated with quantum nonlocality and quantum contextuality. Furthermore, we numerically test this separation on standard machine learning data sets and show that it holds for practical problems. The possibility of quantum advantage demonstrated in this work not only sheds light on the design of useful quantum machine learning protocols but also provides inspiration to draw on ideas from quantum foundations to improve purely classical algorithms.

25 pages, 13 figures

References in corpus (16)

• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• The density-matrix renormalization group in the age of matrix product states
• Quantum computational advantage using photons
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• An introduction to quantum machine learning
• Strong quantum computational advantage using a superconducting quantum processor
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• Quantum simulation of time-dependent Hamiltonians and the convenient illusion of Hilbert space
• Computational power of correlations
• Entanglement Devised Barren Plateau Mitigation
• Barren plateaus preclude learning scramblers
• Quantum Supremacy for Simulating A Translation-Invariant Ising Spin Model
• On the Quantum versus Classical Learnability of Discrete Distributions
• Modeling Pauli measurements on graph states with nearest-neighbor classical communication
• Representing probabilistic data via ontological models
• A simple demonstration of Bell's theorem involving two observers and no probabilities or inequalities

Cited by in corpus (34)

• Quantum Computing for High-Energy Physics: State of the Art and Challenges. Summary of the QC4HEP Working Group
• Kochen-Specker Contextuality
• Quantum Machine Learning: from physics to software engineering
• Generative quantum machine learning via denoising diffusion probabilistic models
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Variational inference with a quantum computer
• A universal neutral-atom quantum computer with individual optical addressing and non-destructive readout
• Generative Quantum Learning of Joint Probability Distribution Functions
• Quantum anomaly detection in the latent space of proton collision events at the LHC
• Interpretable Quantum Advantage in Neural Sequence Learning
• A performance characterization of quantum generative models
• Learning shallow quantum circuits
• Tensor networks for interpretable and efficient quantum-inspired machine learning
• Experimental test of high-dimensional quantum contextuality based on contextuality concentration
• Towards AutoQML: A Cloud-Based Automated Circuit Architecture Search Framework
• Application-Oriented Benchmarking of Quantum Generative Learning Using QUARK
• Decoherence Effects in a Three-Level System under Gaussian Process
• Robust Quantum Reservoir Computing for Molecular Property Prediction
• Quantum delegated and federated learning via quantum homomorphic encryption
• Quantum Inception Score
• Tensor networks and efficient descriptions of classical data
• Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework
• Bosonic Indistinguishability-Dependent Contextuality
• Sampling Problems on a Quantum Computer
• Probing many-body Bell correlation depth with superconducting qubits
• Contextuality of Quantum Error-Correcting Codes
• Quantum Curriculum Learning
• ORQVIZ: Visualizing High-Dimensional Landscapes in Variational Quantum Algorithms
• No-go theorem for environment-assisted invariance in non-unitary dynamics
• Demonstration of sequential processors with quantum advantage and analysis of classical performance limits
• Quantum-assisted tracer dispersion in turbulent shear flow
• Information Processing in Quantum Thermodynamic Systems: an Autonomous Hamiltonian Approach
• Quantum Machine Learning for Climate Modelling
• k-Contextuality as a Heuristic for Memory Separations in Learning