Measurement-Based Quantum Diffusion Models

TL;DR

This paper introduces measurement-based quantum diffusion models that connect classical and quantum diffusion, enabling new quantum state generation methods with rigorous error bounds and theoretical insights.

Contribution

It presents a novel measurement-based framework for quantum diffusion, establishing connections to classical stochastic processes and introducing quantum score matching and Petz recovery maps.

Findings

Quantum score matching is equivalent to learning unitary generators for reverse processes.

Local Petz recovery maps effectively recover states with finite correlation length.

Classical shadow reconstruction provides a general method with rigorous error bounds.

Abstract

We introduce measurement-based quantum diffusion models that bridge classical and quantum diffusion theory through randomized weak measurements. The measurement-based approach naturally generates stochastic quantum trajectories while preserving purity at the trajectory level and inducing depolarization at the ensemble level. We address two quantum state generation problems: trajectory-level recovery of pure state ensembles and ensemble-average recovery of mixed states. For trajectory-level recovery, we establish that quantum score matching is mathematically equivalent to learning unitary generators for the reverse process. For ensemble-average recovery, we introduce local Petz recovery maps for states with finite correlation length and classical shadow reconstruction for general states, both with rigorous error bounds. Our framework establishes Petz recovery maps as quantum generalizations of reverse Fokker-Planck equations, providing a rigorous bridge between quantum recovery channels and classical stochastic reversals. This work enables new approaches to quantum state generation with potential applications in quantum information science.