Generative quantum machine learning via denoising diffusion probabilistic models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Bingzhi, Xu, Peng, Chen, Xiaohui, Zhuang, Quntao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911409484333056
author Zhang, Bingzhi
Xu, Peng
Chen, Xiaohui
Zhuang, Quntao
author_facet Zhang, Bingzhi
Xu, Peng
Chen, Xiaohui
Zhuang, Quntao
contents Deep generative models are key-enabling technology to computer vision, text generation, and large language models. Denoising diffusion probabilistic models (DDPMs) have recently gained much attention due to their ability to generate diverse and high-quality samples in many computer vision tasks, as well as to incorporate flexible model architectures and a relatively simple training scheme. Quantum generative models, empowered by entanglement and superposition, have brought new insight to learning classical and quantum data. Inspired by the classical counterpart, we propose the quantum denoising diffusion probabilistic model (QuDDPM) to enable efficiently trainable generative learning of quantum data. QuDDPM adopts sufficient layers of circuits to guarantee expressivity, while it introduces multiple intermediate training tasks as interpolation between the target distribution and noise to avoid barren plateau and guarantee efficient training. We provide bounds on the learning error and demonstrate QuDDPM's capability in learning correlated quantum noise model, quantum many-body phases, and topological structure of quantum data. The results provide a paradigm for versatile and efficient quantum generative learning.
format Preprint
id arxiv_https___arxiv_org_abs_2310_05866
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generative quantum machine learning via denoising diffusion probabilistic models
Zhang, Bingzhi
Xu, Peng
Chen, Xiaohui
Zhuang, Quntao
Quantum Physics
Artificial Intelligence
Machine Learning
Deep generative models are key-enabling technology to computer vision, text generation, and large language models. Denoising diffusion probabilistic models (DDPMs) have recently gained much attention due to their ability to generate diverse and high-quality samples in many computer vision tasks, as well as to incorporate flexible model architectures and a relatively simple training scheme. Quantum generative models, empowered by entanglement and superposition, have brought new insight to learning classical and quantum data. Inspired by the classical counterpart, we propose the quantum denoising diffusion probabilistic model (QuDDPM) to enable efficiently trainable generative learning of quantum data. QuDDPM adopts sufficient layers of circuits to guarantee expressivity, while it introduces multiple intermediate training tasks as interpolation between the target distribution and noise to avoid barren plateau and guarantee efficient training. We provide bounds on the learning error and demonstrate QuDDPM's capability in learning correlated quantum noise model, quantum many-body phases, and topological structure of quantum data. The results provide a paradigm for versatile and efficient quantum generative learning.
title Generative quantum machine learning via denoising diffusion probabilistic models
topic Quantum Physics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.05866