Generative model for learning quantum ensemble via optimal transport loss

TL;DR

This paper introduces a quantum generative model for learning quantum ensembles using an optimal transport loss, enabling applications like quantum anomaly detection and device health checks.

Contribution

It proposes a novel quantum generative model utilizing optimal transport loss to learn quantum ensembles, addressing limitations of previous quantum generative approaches.

Findings

Effective in quantum anomaly detection

Analyzes the scaling property of the approximation error

Enables applications like quantum device health checks

Abstract

Generative modeling is an unsupervised machine learning framework, that exhibits strong performance in various machine learning tasks. Recently we find several quantum version of generative model, some of which are even proven to have quantum advantage. However, those methods are not directly applicable to construct a generative model for learning a set of quantum states, i.e., ensemble. In this paper, we propose a quantum generative model that can learn quantum ensemble, in an unsupervised machine learning framework. The key idea is to introduce a new loss function calculated based on optimal transport loss, which have been widely used in classical machine learning due to its several good properties; e.g., no need to ensure the common support of two ensembles. We then give in-depth analysis on this measure, such as the scaling property of the approximation error. We also demonstrate the generative modeling with the application to quantum anomaly detection problem, that cannot be handled via existing methods. The proposed model paves the way for a wide application such as the health check of quantum devices and efficient initialization of quantum computation.