Detecting underdetermination in parameterized quantum circuits

Abstract

A central question in machine learning is how reliable the predictions of a trained model are. Reliability includes the identification of instances for which a model is likely not to be trusted based on an analysis of the learning system itself. Such unreliability for an input may arise from the model family providing a variety of hypotheses consistent with the training data, which can vastly disagree in their predictions on that particular input point. This is called the underdetermination problem, and it is important to develop methods to detect it. With the emergence of quantum machine learning (QML) as a prospective alternative to classical methods for certain learning problems, the question arises to what extent they are subject to underdetermination and whether similar techniques as those developed for classical models can be employed for its detection. In this work, we first provide an overview of concepts from Safe AI and reliability, which in particular received little attention in QML. We then explore the use of a method based on local second-order information for the detection of underdetermination in parameterized quantum circuits through numerical experiments. We further demonstrate that the approach is robust to certain levels of shot noise. Our work contributes to the body of literature on Safe Quantum AI, which is an emerging field of growing importance.

References in corpus (13)

• Barren plateaus in quantum neural network training landscapes
• Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
• Quantum Circuit Learning
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Artificial Intelligence, Values and Alignment
• Data re-uploading for a universal quantum classifier
• Shaping the learning landscape in neural networks around wide flat minima
• Towards quantum enhanced adversarial robustness in machine learning
• Characterizing the loss landscape of variational quantum circuits
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Interpretable Quantum Advantage in Neural Sequence Learning
• Training robust and generalizable quantum models
• Predominant Aspects on Security for Quantum Machine Learning: Literature Review