Transition Role of Entangled Data in Quantum Machine Learning

Abstract

Entanglement serves as the resource to empower quantum computing. Recent progress has highlighted its positive impact on learning quantum dynamics, wherein the integration of entanglement into quantum operations or measurements of quantum machine learning (QML) models leads to substantial reductions in training data size, surpassing a specified prediction error threshold. However, an analytical understanding of how the entanglement degree in data affects model performance remains elusive. In this study, we address this knowledge gap by establishing a quantum no-free-lunch (NFL) theorem for learning quantum dynamics using entangled data. Contrary to previous findings, we prove that the impact of entangled data on prediction error exhibits a dual effect, depending on the number of permitted measurements. With a sufficient number of measurements, increasing the entanglement of training data consistently reduces the prediction error or decreases the required size of the training data to achieve the same prediction error. Conversely, when few measurements are allowed, employing highly entangled data could lead to an increased prediction error. The achieved results provide critical guidance for designing advanced QML protocols, especially for those tailored for execution on early-stage quantum computers with limited access to quantum resources.

Accept to Nature Communications 15, 3716 (2024)

References in corpus (28)

• Training language models to follow instructions with human feedback
• LLaMA: Open and Efficient Foundation Language Models
• Quantum algorithm for solving linear systems of equations
• A Survey of Large Language Models
• An introduction to quantum machine learning
• Challenges and Opportunities in Quantum Machine Learning
• Quantum advantage in learning from experiments
• A rigorous and robust quantum speed-up in supervised machine learning
• Generalization in quantum machine learning from few training data
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• The randomized measurement toolbox
• Experimental demonstration of Shor's algorithm with quantum entanglement
• Information-theoretic bounds on quantum advantage in machine learning
• All entangled states are useful for channel discrimination
• The Principles of Data-Centric AI (DCAI)
• Data-centric Artificial Intelligence: A Survey
• Towards understanding the power of quantum kernels in the NISQ era
• Out-of-distribution generalization for learning quantum dynamics
• Dynamical simulation via quantum machine learning with provable generalization
• Entangled Datasets for Quantum Machine Learning
• An Improved Sample Complexity Lower Bound for (Fidelity) Quantum State Tomography
• Decay and storage of multiparticle entangled states of atoms in collective thermostat
• Preparation of entangled states of two photons in several spatial modes
• On exploring the potential of quantum auto-encoder for learning quantum systems
• Power of Quantum Generative Learning
• The power and limitations of learning quantum dynamics incoherently
• Recent Advances for Quantum Neural Networks in Generative Learning
• Learning quantum processes without input control

Cited by in corpus (2)

• Learning quantum states and unitaries of bounded gate complexity
• Measuring Incompatible Observables with Quantum Neural Networks