Observing Schrödinger's Cat with Artificial Intelligence: Emergent Classicality from Information Bottleneck

Abstract

We train a generative language model on the randomized local measurement data collected from Schrödinger's cat quantum state. We demonstrate that the classical reality emerges in the language model due to the information bottleneck: although our training data contains the full quantum information about Schrödinger's cat, a weak language model can only learn to capture the classical reality of the cat from the data. We identify the quantum-classical boundary in terms of both the size of the quantum system and the information processing power of the classical intelligent agent, which indicates that a stronger agent can realize more quantum nature in the environmental noise surrounding the quantum system. Our approach opens up a new avenue for using the big data generated on noisy intermediate-scale quantum (NISQ) devices to train generative models for representation learning of quantum operators, which might be a step toward our ultimate goal of creating an artificial intelligence quantum physicist.

arXiv comment17 pages, 9 figures

References in corpus (48)

• Quantum Computing in the NISQ era and beyond
• The information bottleneck method
• Decoherence, the measurement problem, and interpretations of quantum mechanics
• Models of Wave-function Collapse, Underlying Theories, and Experimental Tests
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Power of data in quantum machine learning
• Efficient quantum state tomography
• Quantum Darwinism
• Quantum advantage in learning from experiments
• Quantum probabilities as Bayesian probabilities
• Discovering physical concepts with neural networks
• Quantum Mechanics as Quantum Information (and only a little more)
• Quantum Tomography via Compressed Sensing: Error Bounds, Sample Complexity, and Efficient Estimators
• The randomized measurement toolbox
• Quantum-Bayesian Coherence: The No-Nonsense Version
• Reconstructing quantum states with generative models
• Information-theoretic bounds on quantum advantage in machine learning
• Efficient tomography of a quantum many-body system
• Provably efficient machine learning for quantum many-body problems
• Decoherence, Einselection, and the Existential Interpretation (the Rough Guide)
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• Latent Space Purification via Neural Density Operators
• Generic emergence of classical features in quantum Darwinism
• Quantum Foundations in the Light of Quantum Information
• Conditions for compatibility of quantum state assignments
• Classical Shadow Tomography with Locally Scrambled Quantum Dynamics
• Efficient and feasible state tomography of quantum many-body systems
• Neural network quantum state tomography in a two-qubit experiment
• Shadows of quantum machine learning
• Attention-based Quantum Tomography
• Neural-network quantum state tomography
• Scalable and Flexible Classical Shadow Tomography with Tensor Networks
• Probabilistic Simulation of Quantum Circuits with the Transformer
• The Gaussian equivalence of generative models for learning with shallow neural networks
• Operator relaxation and the optimal depth of classical shadows
• Going Beyond Bell's Theorem
• Data-driven emergence of convolutional structure in neural networks
• Scalable Quantum Tomography with Fidelity Estimation
• Operationally meaningful representations of physical systems in neural networks
• Neural network state estimation for full quantum state tomography
• Neural network enhanced measurement efficiency for molecular groundstates
• Emergent classicality in general multipartite states and channels
• Whenever a quantum environment emerges as a classical system, it behaves like a measuring apparatus
• Neural-Shadow Quantum State Tomography
• Explainable Representation Learning of Small Quantum States
• Hardware-efficient learning of quantum many-body states
• Threshold size for the emergence of a classical-like behaviour
• Neural networks trained with SGD learn distributions of increasing complexity

Cited by in corpus (4)

• Demonstration of Robust and Efficient Quantum Property Learning with Shallow Shadows
• Machine Learning the Operator Content of the Critical Self-Dual Ising-Higgs Gauge Model
• Holographic Classical Shadow Tomography
• Neural network enhanced cross entropy benchmark for monitored circuits