Machine learning optimization of Majorana hybrid nanowires

TL;DR

This paper demonstrates that machine learning, specifically CMA-ES, can effectively tune Majorana nanowires with disorder, restoring topological properties and Majorana zero modes with minimal gates.

Contribution

It introduces a machine learning approach to optimize gate voltages in disordered Majorana wires, enabling disorder effects to be eliminated.

Findings

CMA-ES efficiently improves topological signatures.

The algorithm learns intrinsic disorder profiles.

Disorder effects can be fully eliminated with 20 gates.

Abstract

As the complexity of quantum systems such as quantum bit arrays increases, efforts to automate expensive tuning are increasingly worthwhile. We investigate machine learning based tuning of gate arrays using the CMA-ES algorithm for the case study of Majorana wires with strong disorder. We find that the algorithm is able to efficiently improve the topological signatures, learn intrinsic disorder profiles, and completely eliminate disorder effects. For example, with only 20 gates, it is possible to fully recover Majorana zero modes destroyed by disorder by optimizing gate voltages.