Transition Role of Entangled Data in Quantum Machine Learning
arXiv:2306.03481 · doi:10.1038/s41467-024-47983-1
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 (46)
- Quantum Computing in the NISQ era and beyond
- Quantum Machine Learning
- A variational eigenvalue solver on a quantum processor
- Training language models to follow instructions with human feedback
- LLaMA: Open and Efficient Foundation Language Models
- Quantum algorithm for solving linear systems of equations
- Supervised learning with quantum enhanced feature spaces
- A Survey of Large Language Models
- Quantum principal component analysis
- An introduction to quantum machine learning
- Predicting Many Properties of a Quantum System from Very Few Measurements
- Challenges and Opportunities in Quantum Machine Learning
- On the role of entanglement in quantum computational speed-up
- Quantum optimization using variational algorithms on near-term quantum devices
- A rigorous and robust quantum speed-up in supervised machine learning
- Quantum advantage in learning from experiments
- Quantum machine learning: a classical perspective
- 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
- Quantum-assisted quantum compiling
- Experimental demonstration of Shor's algorithm with quantum entanglement
- Information-theoretic bounds on quantum advantage in machine learning
- Variational Fast Forwarding for Quantum Simulation Beyond the Coherence Time
- All entangled states are useful for channel discrimination
- Optimal quantum learning of a unitary transformation
- Data-centric Artificial Intelligence: A Survey
- The Principles of Data-Centric AI (DCAI)
- Towards understanding the power of quantum kernels in the NISQ era
- Out-of-distribution generalization for learning quantum dynamics
- Minimally-Entangled State Preparation of Localized Wavefunctions on Quantum Computers
- Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
- Robust quantum compilation and circuit optimisation via energy minimisation
- More entanglement implies higher performance in tailored channel discrimination tasks
- Preparation of entangled states through Hilbert space engineering
- Dynamical simulation via quantum machine learning with provable generalization
- Quantum Differentially Private Sparse Regression Learning
- 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