Learning to predict arbitrary quantum processes

In this talk, Dr Chen will present an efficient machine learning (ML) algorithm for predicting any unknown quantum process E over n qubits. For a wide range of distributions D on arbitrary n-qubit states, Dr Chen shows that this ML algorithm can learn to predict any local property of the output from the unknown process E, with a small average error over input states drawn from D. The ML algorithm is computationally efficient even when the unknown process is a quantum circuit with exponentially many gates. The algorithm combines efficient procedures for learning properties of an unknown state and for learning a low-degree approximation to an unknown observable. The analysis hinges on proving new norm inequalities, including a quantum analogue of the classical Bohnenblust-Hille inequality, which we derive by giving an improved algorithm for optimizing local Hamiltonians. Overall, the results highlight the potential for ML models to predict the output of complex quantum dynamics much faster than the time needed to run the process itself.

This online talk will be 45 minutes, with 15 minutes for questions.