Quantum Latent Diffusion Models

Abstract

The introduction of quantum concepts is increasingly making its way into generative machine learning models. However, while there are various implementations of quantum Generative Adversarial Networks, the integration of quantum elements into diffusion models remains an open and challenging task. In this work, we propose a potential version of a quantum diffusion model that leverages the established idea of classical latent diffusion models. This involves using a traditional autoencoder to reduce images, followed by operations with variational circuits in the latent space. To effectively assess the benefits brought by quantum computing, the images generated by the quantum latent diffusion model have been compared to those generated by a classical model with a similar number of parameters, evaluated in terms of quantitative metrics. The results demonstrate an advantage in using a quantum version, as evidenced by obtaining better metrics for the images generated by the quantum version compared to those obtained by the classical version. Furthermore, quantum models continue to outperform even when considering small percentages of the dataset for training, demonstrating the quantum's ability to extract features more effectively even in a few shot learning scenario.

40 pages, 15 figures, 5 tables

References in corpus (19)

• Variational Quantum Algorithms
• Surface codes: Towards practical large-scale quantum computation
• Quantum principal component analysis
• Parameterized quantum circuits as machine learning models
• Suppressing quantum errors by scaling a surface code logical qubit
• Quantum Error Mitigation
• Quantum Data Fitting
• Quantum advantage with shallow circuits
• The Expressive Power of Parameterized Quantum Circuits
• Experimental Quantum Generative Adversarial Networks for Image Generation
• Implementing a distance-based classifier with a quantum interference circuit
• Quantum Image Processing and Its Application to Edge Detection: Theory and Experiment
• Quantum advantage with noisy shallow circuits in 3D
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Quantum error mitigation via matrix product operators
• Can Error Mitigation Improve Trainability of Noisy Variational Quantum Algorithms?
• Quantum-Noise-Driven Generative Diffusion Models
• Resource Saving via Ensemble Techniques for Quantum Neural Networks
• A General Approach to Dropout in Quantum Neural Networks