Measurement-Induced Quantum Neural Network

TL;DR

This paper introduces a measurement-induced quantum neural network architecture that uses adaptive measurements to create nonlinear, history-dependent quantum dynamics, enabling applications in optimization and classification.

Contribution

It proposes a novel variational quantum neural network architecture based on monitored circuits with adaptive measurements, distinct from traditional random sampling methods.

Findings

Effective training demonstrated on various tasks

Broad performance across different monitoring rates

Feasible implementation with matchgate-based fermionic simulation

Abstract

We introduce a measurement-induced quantum neural network (MINN), an adaptive monitored-circuit architecture in which mid-circuit measurement outcomes determine the entangling gates in subsequent layers. In contrast to standard monitored circuits where sites and gates are sampled randomly, the gates are parametrized and variational, producing correlated history-dependent dynamics and injecting nonlinearity through measurement back-action. A generic MINN is not expected to be efficiently classically simulable. To demonstrate feasibility, we study a matchgate MINN that admits exact fermionic simulation and can be trained with gradient estimators. We apply the architecture to continuous optimization, image classification, and ground-state search in the Sherrington-Kirkpatrick spin glass, finding effective training and performance over a broad range of monitoring rates.