Quantifying the Expressive Capacity of Quantum Systems: Fundamental Limits and Eigentasks
arXiv:2301.00042
Abstract
The expressive capacity of quantum systems for machine learning is limited by quantum sampling noise incurred during measurement. Although it is generally believed that noise limits the resolvable capacity of quantum systems, the precise impact of noise on learning is not yet fully understood. We present a mathematical framework for evaluating the available expressive capacity of general quantum systems from a finite number of measurements, and provide a methodology for extracting the extrema of this capacity, its eigentasks. Eigentasks are a native set of functions that a given quantum system can approximate with minimal error. We show that extracting low-noise eigentasks leads to improved performance for machine learning tasks such as classification, displaying robustness to overfitting. We obtain a tight bound on the expressive capacity, and present analyses suggesting that correlations in the measured quantum system enhance learning capacity by reducing noise in eigentasks. These results are supported by experiments on superconducting quantum processors. Our findings have broad implications for quantum machine learning and sensing applications.
arXiv comment7 + 21 pages, 4 + 12 figures, 1 table
References in corpus (16)
- Variational Quantum Algorithms
- Supervised learning with quantum enhanced feature spaces
- Quantum metrology
- The Role of Relative Entropy in Quantum Information Theory
- Unified View of Quantum and Classical Correlations
- The effect of data encoding on the expressive power of variational quantum machine learning models
- Connecting ansatz expressibility to gradient magnitudes and barren plateaus
- Procedure for systematically tuning up crosstalk in the cross resonance gate
- Robust data encodings for quantum classifiers
- The Expressive Power of Parameterized Quantum Circuits
- Effect of barren plateaus on gradient-free optimization
- Optimal metrology with programmable quantum sensors
- Sample-efficient learning of quantum many-body systems
- Dynamical phase transitions in quantum reservoir computing
- Natural quantum reservoir computing for temporal information processing
- Scalable photonic platform for real-time quantum reservoir computing