Learning Unitaries by Gradient Descent

Abstract

We study the hardness of learning unitary transformations in $U(d)$ via gradient descent on time parameters of alternating operator sequences. We provide numerical evidence that, despite the non-convex nature of the loss landscape, gradient descent always converges to the target unitary when the sequence contains $d^2$ or more parameters. Rates of convergence indicate a "computational phase transition." With less than $d^2$ parameters, gradient descent converges to a sub-optimal solution, whereas with more than $d^2$ parameters, gradient descent converges exponentially to an optimal solution.

References in corpus (6)

• A Quantum Approximate Optimization Algorithm
• A Quantum Approximate Optimization Algorithm Applied to a Bounded Occurrence Constraint Problem
• Quantum approximate optimization is computationally universal
• Searching for quantum optimal controls under severe constraints
• Quantum Control Landscapes Are Almost Always Trap Free
• Efficient implementation of unitary transformations