Machine Learning-aided Optimal Control of a noisy qubit

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cantone, Riccardo, Mukherjee, Shreyasi, Giannelli, Luigi, Paladino, Elisabetta, Falci, Giuseppe
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913948775743488
author Cantone, Riccardo
Mukherjee, Shreyasi
Giannelli, Luigi
Paladino, Elisabetta
Falci, Giuseppe
author_facet Cantone, Riccardo
Mukherjee, Shreyasi
Giannelli, Luigi
Paladino, Elisabetta
Falci, Giuseppe
contents We apply a graybox machine-learning framework to model and control a qubit undergoing Markovian and non-Markovian dynamics from environmental noise. The approach combines physics-informed equations with a lightweight transformer neural network based on the self-attention mechanism. The model is trained on simulated data and learns an effective operator that predicts observables accurately, even in the presence of memory effects. We benchmark both non-Gaussian random-telegraph noise and Gaussian Ornstein-Uhlenbeck noise and achieve low prediction errors even in challenging noise coupling regimes. Using the model as a dynamics emulator, we perform gradient-based optimal control to identify pulse sequences implementing a universal set of single-qubit gates, achieving fidelities above 99% for the lowest considered value of the coupling and remaining above 90% for the highest.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Machine Learning-aided Optimal Control of a noisy qubit
Cantone, Riccardo
Mukherjee, Shreyasi
Giannelli, Luigi
Paladino, Elisabetta
Falci, Giuseppe
Quantum Physics
Other Condensed Matter
We apply a graybox machine-learning framework to model and control a qubit undergoing Markovian and non-Markovian dynamics from environmental noise. The approach combines physics-informed equations with a lightweight transformer neural network based on the self-attention mechanism. The model is trained on simulated data and learns an effective operator that predicts observables accurately, even in the presence of memory effects. We benchmark both non-Gaussian random-telegraph noise and Gaussian Ornstein-Uhlenbeck noise and achieve low prediction errors even in challenging noise coupling regimes. Using the model as a dynamics emulator, we perform gradient-based optimal control to identify pulse sequences implementing a universal set of single-qubit gates, achieving fidelities above 99% for the lowest considered value of the coupling and remaining above 90% for the highest.
title Machine Learning-aided Optimal Control of a noisy qubit
topic Quantum Physics
Other Condensed Matter
url https://arxiv.org/abs/2507.14085