A thresholding bandit algorithm on data from a single-parameter entanglement-witness family enables conclusive batch entanglement detection for two-qubit states in class F, with MAB-derived sample-complexity bounds.
Multi-armed quantum bandits: Exploration versus exploitation when learning properties of quantum states
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
quant-ph 2verdicts
UNVERDICTED 2representative citing papers
A classical agent extracts more work from quantum temporal correlations via adaptive strategies bounded by the new Time-Ordered Free Energy, while reinforcement learning achieves polylogarithmic dissipation when learning unknown states.
citing papers explorer
-
Batch Entanglement Detection in Parameterized Qubit States using Classical Bandit Algorithms
A thresholding bandit algorithm on data from a single-parameter entanglement-witness family enables conclusive batch entanglement detection for two-qubit states in class F, with MAB-derived sample-complexity bounds.
-
A Demon that remembers: An agential approach towards quantum thermodynamics of temporal correlations
A classical agent extracts more work from quantum temporal correlations via adaptive strategies bounded by the new Time-Ordered Free Energy, while reinforcement learning achieves polylogarithmic dissipation when learning unknown states.