Statistical Complexity of Quantum Learning

Abstract

Recent years have seen significant activity on the problem of using data for the purpose of learning properties of quantum systems or of processing classical or quantum data via quantum computing. As in classical learning, quantum learning problems involve settings in which the mechanism generating the data is unknown, and the main goal of a learning algorithm is to ensure satisfactory accuracy levels when only given access to data and, possibly, side information such as expert knowledge. This article reviews the complexity of quantum learning using information-theoretic techniques by focusing on data complexity, copy complexity, and model complexity. Copy complexity arises from the destructive nature of quantum measurements, which irreversibly alter the state to be processed, limiting the information that can be extracted about quantum data. For example, in a quantum system, unlike in classical machine learning, it is generally not possible to evaluate the training loss simultaneously on multiple hypotheses using the same quantum data. To make the paper self-contained and approachable by different research communities, we provide extensive background material on classical results from statistical learning theory, as well as on the distinguishability of quantum states. Throughout, we highlight the differences between quantum and classical learning by addressing both supervised and unsupervised learning, and we provide extensive pointers to the literature.

References in corpus (22)

• Power of data in quantum machine learning
• Quantum Illumination with Gaussian States
• Quantum advantage in learning from experiments
• Generalization in quantum machine learning from few training data
• Information-theoretic bounds on quantum advantage in machine learning
• Provably efficient machine learning for quantum many-body problems
• Theory of overparametrization in quantum neural networks
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Learning Quantum Systems
• Experimental quantum adversarial learning with programmable superconducting qubits
• The Quantum Wasserstein Distance of Order 1
• On the statistical complexity of quantum circuits
• Explicit Learning Curves for Transduction and Application to Clustering and Compression Algorithms
• Entropic information-disturbance tradeoff
• Structural risk minimization for quantum linear classifiers
• Quantum learning of coherent states
• Quantum Mixed State Compiling
• Quantum-enhanced barcode decoding and pattern recognition
• Effects of quantum resources on the statistical complexity of quantum circuits
• How to enhance quantum generative adversarial learning of noisy information
• Universal algorithms for quantum data learning

Cited by in corpus (8)

• Accuracy vs Memory Advantage in the Quantum Simulation of Stochastic Processes
• Quantum learning advantage on a scalable photonic platform
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits
• Quantum delegated and federated learning via quantum homomorphic encryption
• Single-shot quantum machine learning
• Out-of-distribution generalisation for learning quantum channels with low-energy coherent states
• Analysis of Quantum Image Representations for Supervised Classification
• Quantum phase classification via partial tomography-based quantum hypothesis testing