Measurement disturbance tradeoffs in three-qubit unsupervised quantum classification
arXiv:2202.05584 · doi:10.1103/PhysRevA.105.062447
Abstract
We consider measurement disturbance tradeoffs in quantum machine learning protocols which seek to learn about quantum data. We study the simplest example of a binary classification task, in the unsupervised regime. Specifically, we investigate how a classification of two qubits, that can each be in one of two unknown states, affects our ability to perform a subsequent classification on three qubits when a third is added. Surprisingly, we find a range of strategies in which a non-trivial first classification does not affect the success rate of the second classification. There is, however, a non-trivial measurement disturbance tradeoff between the success rate of the first and second classifications, and we fully characterise this tradeoff analytically.
References in corpus (17)
- Quantum State Disturbance vs. Information Gain: Uncertainty Relations for Quantum Information
- Minimum-error discrimination between three mirror-symmetric states
- A universal programmable quantum state discriminator that is optimal for unambiguously distinguishing between unknown states
- Local discrimination of mixed states
- Comparison of two unknown pure quantum states
- Extracting information from a qubit by multiple observers: Toward a theory of sequential state discrimination
- Quantum Template Matching
- A Return to the Optimal Detection of Quantum Information
- Quantum learning: optimal classification of qubit states
- Multiple-copy state discrimination: Thinking globally, acting locally
- Inductive supervised quantum learning
- Difficulty of distinguishing product states locally
- Unsupervised classification of quantum data
- Changepoint Problem in Quantumn Setting
- Sequential discrimination of qudits by multiple observers
- Post-processing of quantum instruments
- Extracting unambiguous information from a single qubit by sequential observers