Impact of measurement noise on escaping saddles in variational quantum algorithms

TL;DR

This paper studies how measurement noise in quantum computing affects optimization processes, showing that noise can help escape from problematic points in the optimization landscape.

Contribution

The paper introduces a theoretical framework linking measurement noise to escape dynamics in variational quantum algorithms using stochastic differential equations.

Findings

Escape time scales as a power law with respect to $\eta /N_s$.

Measurement noise facilitates escape from saddle points in non-convex landscapes.

Stochastic differential equations accurately model transient escape dynamics.

Abstract

Stochastic gradient descent (SGD) is a widely used optimization technique in classical machine learning and the Variational Quantum Eigensolver (VQE). In VQE implementations on quantum hardware, measurement shot noise is inevitable. We analyze how this noise affects optimization dynamics, especially escape from saddle points in non-convex loss landscapes. Our simulations show that the escape time scales as a power law with respect to \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\eta /N_s$$\end{document}, where \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\eta$$\end{document} is the learning rate and \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$N_s$$\end{document} is the number of measurements. Through SGD analysis, we provide theoretical insight into how measurement noise facilitates escape. In particular, we demonstrate that a continuous-time approximation via stochastic differential equations (SDE) accurately captures the transient escape dynamics. This suggests that \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\eta /N_s$$\end{document} represents effective noise strength, indicating that increasing \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\eta$$\end{document} or decreasing \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$N_s$$\end{document} has similar effects. While concerns exist about the SDE’s validity in stationary regimes, our findings clarify its applicability to transient behavior. Our work improves understanding of the role of measurement noise in VQE optimization.

Figures