Artificial intelligence for representing and characterizing quantum systems

Abstract

Efficient characterization of large-scale quantum systems, especially those produced by quantum analog simulators and megaquop quantum computers, poses a central challenge in quantum science due to the exponential scaling of the Hilbert space with respect to system size. Recent advances in artificial intelligence (AI), with its aptitude for high-dimensional pattern recognition and function approximation, have emerged as a powerful tool to address this challenge. A growing body of research has leveraged AI to represent and characterize scalable quantum systems, spanning from theoretical foundations to experimental realizations. Depending on how prior knowledge and learning architectures are incorporated, the integration of AI into quantum system characterization can be categorized into three synergistic paradigms: machine learning, and, in particular, deep learning and language models. This review discusses how each of these AI paradigms contributes to two core tasks in quantum systems characterization: quantum property prediction and the construction of surrogates for quantum states. These tasks underlie diverse applications, from quantum certification and benchmarking to the enhancement of quantum algorithms and the understanding of strongly correlated phases of matter. Key challenges and open questions are also discussed, together with future prospects at the interface of AI and quantum science.

32 pages. Comments are welcome

References in corpus (118)

• Quantum entanglement
• Variational Quantum Algorithms
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Noisy intermediate-scale quantum (NISQ) algorithms
• A Survey on Large Language Model based Autonomous Agents
• Scaling Laws for Neural Language Models
• Improved Simulation of Stabilizer Circuits
• Machine learning phases of matter
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Logical quantum processor based on reconfigurable atom arrays
• Learning phase transitions by confusion
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Quantum error correction below the surface code threshold
• Tensor networks for complex quantum systems
• Discovering physical concepts with neural networks
• A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT
• The randomized measurement toolbox
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Quantum certification and benchmarking
• Improved classical simulation of quantum circuits dominated by Clifford gates
• Reconstructing quantum states with generative models
• Active learning machine learns to create new quantum experiments
• Neural-Network Approach to Dissipative Quantum Many-Body Dynamics
• Deep autoregressive models for the efficient variational simulation of many-body quantum systems
• Engineered Dissipation for Quantum Information Science
• Automated Search for new Quantum Experiments
• Artificial Intelligence and Machine Learning for Quantum Technologies
• Cross-Platform Verification of Intermediate Scale Quantum Devices
• Learning Quantum Systems
• Machine learning meets quantum physics
• Beyond-classical computation in quantum simulation
• A tweezer array with 6100 highly coherent atomic qubits
• Neural tensor contractions and the expressive power of deep neural quantum states
• Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
• A Tutorial on Quantum Master Equations: Tips and tricks for quantum optics, quantum computing and beyond
• Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network
• Efficient quantum state tomography with convolutional neural networks
• Empowering deep neural quantum states through efficient optimization
• Quantum circuit optimization with deep reinforcement learning
• A polynomial-time classical algorithm for noisy random circuit sampling
• The Meta-Variational Quantum Eigensolver (Meta-VQE): Learning energy profiles of parameterized Hamiltonians for quantum simulation
• Entanglement Classification via Neural Network Quantum States
• Benchmarking quantum computers
• Machine Learning for Practical Quantum Error Mitigation
• Hamiltonian Learning for Quantum Error Correction
• High-coherence superconducting qubits made using industry-standard, advanced semiconductor manufacturing
• Benchmarking highly entangled states on a 60-atom analog quantum simulator
• Shallow shadows: Expectation estimation using low-depth random Clifford circuits
• Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
• Quantum coarsening and collective dynamics on a programmable simulator
• Non-Abelian braiding of Fibonacci anyons with a superconducting processor
• Classical surrogates for quantum learning models
• Graph neural network initialisation of quantum approximate optimisation
• Probing post-measurement entanglement without post-selection
• Machine learning discovery of new phases in programmable quantum simulator snapshots
• Artificial Intelligence for Quantum Computing
• Learning Quantum Hamiltonians from Single-qubit Measurements
• Beyond NISQ: The Megaquop Machine
• Improved machine learning algorithm for predicting ground state properties
• Neural-Network Decoders for Measurement Induced Phase Transitions
• Scalable Hamiltonian learning for large-scale out-of-equilibrium quantum dynamics
• Neural networks for detecting multimode Wigner-negativity
• Flexible learning of quantum states with generative query neural networks
• Quantum circuit synthesis with diffusion models
• Learnability transitions in monitored quantum dynamics via eavesdropper's classical shadows
• Data-Enhanced Variational Monte Carlo Simulations for Rydberg Atom Arrays
• Learning Interpretable Representations of Entanglement in Quantum Optics Experiments using Deep Generative Models
• Deep Learning of Quantum Many-Body Dynamics via Random Driving
• Quantum circuit fidelity estimation using machine learning
• Learning shallow quantum circuits
• Demonstration of Robust and Efficient Quantum Property Learning with Shallow Shadows
• Formation of stripes in a mixed-dimensional cold-atom Fermi-Hubbard system
• Machine learning on quantum experimental data toward solving quantum many-body problems
• Simultaneous Discovery of Quantum Error Correction Codes and Encoders with a Noise-Aware Reinforcement Learning Agent
• Potential and limitations of random Fourier features for dequantizing quantum machine learning
• Foundation Neural-Networks Quantum States as a Unified Ansatz for Multiple Hamiltonians
• QuEst: Graph Transformer for Quantum Circuit Reliability Estimation
• Transformer neural networks and quantum simulators: a hybrid approach for simulating strongly correlated systems
• Experimental demonstration of adversarial examples in learning topological phases
• Unleashing the Potential of LLMs for Quantum Computing: A Study in Quantum Architecture Design
• Sample-efficient estimation of entanglement entropy through supervised learning
• Deep learning of many-body observables and quantum information scrambling
• Quantum Circuit Synthesis and Compilation Optimization: Overview and Prospects
• Explainable Representation Learning of Small Quantum States
• On establishing learning separations between classical and quantum machine learning with classical data
• Reconstructing effective Hamiltonians from nonequilibrium (pre-)thermal steady states
• Unsupervised Interpretable Learning of Phases From Many-Qubit Systems
• The generative quantum eigensolver (GQE) and its application for ground state search
• Adversarial Machine Learning Phases of Matter
• Exponential separations between classical and quantum learners
• Efficient Learning of Quantum States Prepared With Few Non-Clifford Gates
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits
• Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum Algorithms
• Noise-Agnostic Quantum Error Mitigation with Data Augmented Neural Models
• Classically Approximating Variational Quantum Machine Learning with Random Fourier Features
• Learning to rank quantum circuits for hardware-optimized performance enhancement
• Transformer-QEC: Quantum Error Correction Code Decoding with Transferable Transformers
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Quantum State Tomography Inspired by Language Modeling
• Predicting Properties of Quantum Systems with Conditional Generative Models
• Learning quantum states prepared by shallow circuits in polynomial time
• Mind the gaps: The fraught road to quantum advantage
• When can classical neural networks represent quantum states?
• Quantum circuit complexity and unsupervised machine learning of topological order
• Efficient Learning of Long-Range and Equivariant Quantum Systems
• ShadowGPT: Learning to Solve Quantum Many-Body Problems from Randomized Measurements
• Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction
• Quantum computing and artificial intelligence: status and perspectives
• When Quantum and Classical Models Disagree: Learning Beyond Minimum Norm Least Square
• Accurate Learning of Equivariant Quantum Systems from a Single Ground State
• Interpretable Machine Learning in Physics: A Review
• Learning measurement-induced phase transitions using attention
• Concept learning of parameterized quantum models from limited measurements
• Quantum Process Learning Through Neural Emulation
• On the hardness of learning ground state entanglement of geometrically local Hamiltonians
• Generative Decoding for Quantum Error-correcting Codes
• Machine learning the effects of many quantum measurements