Machine Learning and Time-Series Decomposition for Phase Extraction and Symbol Classification in CV-QKD

The predictability of phase estimation and symbol classification using machine learning (ML) for experimental continuous-variable quantum key distribution (CV-QKD) is investigated. ML outperforms standard techniques, with up to 2.3% enhancement in the symbol accuracy, showcasing classical noise impact. The time-series decomposition method upper-bounds the predictable space due to shot noise. Ultimately, a 1 kbits/s secret key rate is achieved at 20 km for a 1.8 pW symbol power.