A Survey of Quantum Learning Theory
arXiv:1701.06806
Abstract
This paper surveys quantum learning theory: the theoretical aspects of machine learning using quantum computers. We describe the main results known for three models of learning: exact learning from membership queries, and Probably Approximately Correct (PAC) and agnostic learning from classical or quantum examples.
26 pages LaTeX. v2: many small changes to improve the presentation. This version will appear as Complexity Theory Column in SIGACT News in June 2017. v3: fixed a small ambiguity in the definition of gamma(C) and updated a reference
References in corpus (2)
Cited by in corpus (17)
- Noisy intermediate-scale quantum (NISQ) algorithms
- Quantum machine learning: a classical perspective
- The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
- Learning with Errors is easy with quantum samples
- Benchmarking neural networks for quantum computation
- Machine learning \& artificial intelligence in the quantum domain
- New Trends in Quantum Machine Learning
- Sublinear quantum algorithms for training linear and kernel-based classifiers
- Quantum statistical query learning
- Quantum exploration algorithms for multi-armed bandits
- Quantum Semi-Supervised Kernel Learning
- Two new results about quantum exact learning
- Variational quantum simulation of long-range interacting systems
- Generative Invertible Quantum Neural Networks
- Improved Quantum Boosting
- Quantum Spectral Clustering through a Biased Phase Estimation Algorithm
- Quantum Learning Algorithms and Post-Quantum Cryptography