Effects of quantum resources on the statistical complexity of quantum circuits

Abstract

We investigate how the addition of quantum resources changes the statistical complexity of quantum circuits by utilizing the framework of quantum resource theories. Measures of statistical complexity that we consider include the Rademacher complexity and the Gaussian complexity, which are well-known measures in computational learning theory that quantify the richness of classes of real-valued functions. We derive bounds for the statistical complexities of quantum circuits that have limited access to certain resources and apply our results to two special cases: (1) stabilizer circuits that are supplemented with a limited number of T gates and (2) instantaneous quantum polynomial-time Clifford circuits that are supplemented with a limited number of CCZ gates. We show that the increase in the statistical complexity of a quantum circuit when an additional quantum channel is added to it is upper bounded by the free robustness of the added channel. Finally, we derive bounds for the generalization error associated with learning from training data arising from quantum circuits.

arXiv comment6+6 pages

References in corpus (47)

• Quantum entanglement
• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Quantum algorithm for solving linear systems of equations
• Variational Quantum Algorithms
• Quantifying Coherence
• Supervised learning with quantum enhanced feature spaces
• Quantum support vector machine for big data classification
• A Quantum Approximate Optimization Algorithm
• Quantum Coherence as a Resource
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Improved Simulation of Stabilizer Circuits
• Quantum Chemistry in the Age of Quantum Computing
• Quantum principal component analysis
• Error mitigation for short-depth quantum circuits
• Quantum Resource Theories
• Efficient Learning for Deep Quantum Neural Networks
• Quantum algorithms for supervised and unsupervised machine learning
• Quantum machine learning: a classical perspective
• The Resource Theory of Stabilizer Computation
• Instantaneous non-local computation of low T-depth quantum circuits
• The Heisenberg Representation of Quantum Computers
• Generalized Unitary Coupled Cluster Wavefunctions for Quantum Computation
• Application of a resource theory for magic states to fault-tolerant quantum computing
• Classical simulation of commuting quantum computations implies collapse of the polynomial hierarchy
• A mathematical theory of resources
• Average-case complexity versus approximate simulation of commuting quantum computations
• Exploring Generalization in Deep Learning
• Matchgates and classical simulation of quantum circuits
• Achieving quantum supremacy with sparse and noisy commuting quantum computations
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Quantifying Superposition
• Quantifying the magic of quantum channels
• Unital Quantum Channels - Convex Structure and Revivals of Birkhoff's Theorem
• Norm-Based Capacity Control in Neural Networks
• How many qubits are needed for quantum computational supremacy?
• Optimal resource cost for error mitigation
• Efficient classical simulation of matchgate circuits with generalized inputs and measurements
• On the statistical complexity of quantum circuits
• Efficient classical simulation of Clifford circuits with nonstabilizer input states
• Pseudo-dimension of quantum circuits
• Further extensions of Clifford circuits and their classical simulation complexities
• Efficient classical simulation of noisy quantum computation
• Computational power of matchgates with supplementary resources
• Depth-Width Trade-offs for Neural Networks via Topological Entropy

Cited by in corpus (8)

• A comprehensive review of Quantum Machine Learning: from NISQ to Fault Tolerance
• Understanding quantum machine learning also requires rethinking generalization
• Learning Quantum Processes and Hamiltonians via the Pauli Transfer Matrix
• Generalization of Quantum Machine Learning Models Using Quantum Fisher Information Metric
• Magic Resource Can Enhance the Quantum Capacity of Channels
• Statistical Complexity of Quantum Learning
• Magic of Random Matrix Product States
• Coherence and Imaginarity as Resources in Quantum Circuit Complexity