Learning Time-Varying Gaussian Quantum Lossy Channels

Abstract

Time-varying quantum channels are essential for modeling realistic quantum systems with evolving noise properties. Here, we consider Gaussian lossy channels varying from one use to another and we employ neural networks to classify, regress, and forecast the behavior of these channels from their Choi-Jamiolkowski states. The networks achieve at least 87% of accuracy in distinguishing between non-Markovian, Markovian, memoryless, compound, and deterministic channels. In regression tasks, the model accurately reconstructs the loss parameter sequences, and in forecasting, it predicts future values, with improved performance as the memory parameter approaches 1 for Markovian channels. These results demonstrate the potential of neural networks in characterizing and predicting the dynamics of quantum channels.