Adaptive quantum state tomography with neural networks

Current algorithms for quantum state tomography (QST) are costly both experimentally and computationally. The authors introduce neural adaptive quantum state tomography (NAQT), a fast, flexible machine-learning-based algorithm that adapts measurements and provides orders-of-magnitude faster processing while retaining state-of-the-art reconstruction accuracy. NAQT integrates measurement adaptation and statistical inference via a neural-network replacement of the Bayesian update, avoiding particle-weight decay and costly resampling. It falls under meta-learning (learning to learn quantum states), requires no state ansatz, and can be retrained within hours on a laptop for two-qubit systems, suggesting feasible extension to larger systems and potential speed-ups with added structure.

Yihui Quek, Stanislav Fort, Hui Khoon Ng