Breaking Adiabatic Quantum Control with Deep Learning

TL;DR

This paper combines deep reinforcement learning with shortcuts to adiabaticity to develop fast, robust digital quantum control pulses, surpassing traditional methods and achieving quantum speed limits.

Contribution

It introduces a novel framework integrating DRL and STA for digital quantum control, enhancing speed and robustness without prior analytical guidance.

Findings

DRL produces robust control pulses within quantum speed limits.

Robustness against systematic errors achieved without STA input.

Framework improves quantum information processing efficiency.

Abstract

In the era of digital quantum computing, optimal digitized pulses are requisite for efficient quantum control. This goal is translated into dynamic programming, in which a deep reinforcement learning (DRL) agent is gifted. As a reference, shortcuts to adiabaticity (STA) provide analytical approaches to adiabatic speed up by pulse control. Here, we select single-component control of qubits, resembling the ubiquitous two-level Landau-Zener problem for gate operation. We aim at obtaining fast and robust digital pulses by combining STA and DRL algorithm. In particular, we find that DRL leads to robust digital quantum control with operation time bounded by quantum speed limits dictated by STA. In addition, we demonstrate that robustness against systematic errors can be achieved by DRL without any input from STA. Our results introduce a general framework of digital quantum control, leading to a promising enhancement in quantum information processing.