Machine Learning Reliability Assessment from Application to Pulse Level

In the past few years, we have been witnessing the development of quantum hardware and the rise of new quantum algorithms that can take advantage of these quantum devices. One of the primary challenges in current and near-term quantum computers is the noise in the quantum hardware. To unlock the power of quantum computers noise should be suppressed. Error mitigation approaches at the software level play a major role in reducing errors in quantum circuits executed on quantum computers. However, their effectiveness is dependent on how accurate the noise modeling of the quantum hardware is. In this chapter, we review our recent works in machine learning for quantum circuit reliability assessment and extend our analysis to the pulse level. Furthermore, we provide both qualitative and quantitative comparisons across the ML models for different design abstractions.