Detecting Markovianity of Quantum Processes via Recurrent Neural Networks

TL;DR

This paper introduces a Recurrent Neural Network-based method to accurately classify and forecast the Markovian or non-Markovian nature of quantum processes using time series data from Choi states, demonstrating high accuracy across various scenarios.

Contribution

The paper presents a novel application of RNNs for classifying quantum process Markovianity, achieving high accuracy and efficient forecasting, advancing quantum process analysis techniques.

Findings

Model surpasses 95% accuracy in classification

Effective across diverse quantum channels and noise conditions

Demonstrates strong forecasting capabilities for quantum time series

Abstract

We present a novel methodology utilizing Recurrent Neural Networks (RNNs) to classify Markovian and non-Markovian quantum processes, leveraging time series data derived from Choi states. The model exhibits exceptional accuracy, surpassing 95%, across diverse scenarios, including dephasing and Pauli channels in an arbitrary basis, generalized amplitude damping dynamics, and even in the presence of noise. Additionally, the developed model shows efficient forecasting capabilities for the analyzed time series data. These results suggest the potential of RNNs in discerning and predicting the Markovian nature of quantum processes.