Quantum adiabatic machine learning

TL;DR

This paper introduces a quantum adiabatic approach to machine learning and anomaly detection, leveraging quantum evolution for training and testing classifiers, demonstrated on software verification tasks.

Contribution

It presents a novel quantum adiabatic framework for training and testing classifiers, integrating anomaly detection within quantum evolution processes.

Findings

Successfully trains strong classifiers using quantum adiabatic evolution.

Detects anomalies by evolving classifiers on superpositions of inputs.

Applied specifically to software verification and validation.

Abstract

We develop an approach to machine learning and anomaly detection via quantum adiabatic evolution. In the training phase we identify an optimal set of weak classifiers, to form a single strong classifier. In the testing phase we adiabatically evolve one or more strong classifiers on a superposition of inputs in order to find certain anomalous elements in the classification space. Both the training and testing phases are executed via quantum adiabatic evolution. We apply and illustrate this approach in detail to the problem of software verification and validation.