Document type

Master thesis

Publication date

Publication license

cc by-nc-nd (c) Àlex Pujol Vidal, 2023
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/217853

Fundamental principles of Binary Latent Diffusion

Journal Title

Journal ISSN

Volume Title

Related resource

Abstract

In this thesis we explore the fundamental principles of Binary Latent Diffusion Models (BLDM), a novel class of generative models that leverage probabilistic deep latent variable models and diffusion processes to approximate complex data distributions. The research delves into probability theory, generative models, and latent space representations, with a focus on Variational Autoencoders (VAE) that lead to Bernoulli Variational Autoencoders (BVAE). The study provides a comprehensive overview of the foundations of Diffusion Models, leading to the formal definition of Discrete Bernoulli Diffusion Models (DBDM) and its training objective. Both, BVAE and DBDM, are the building blocks of the BLDM. Additionally, a practical application is presented. This exploration highlights the mathematical formalization and implementation strategies for BLDMs, paving the way for future advancements in generative modeling.

Description

Treballs finals del Màster en Matemàtica Avançada, Facultat de Matemàtiques, Universitat de Barcelona: Curs: 2023-2024. Director: Carles Casacuberta i Sergio Escalera Guerrero

Citation

Citation

PUJOL VIDAL, Àlex. Fundamental principles of Binary Latent Diffusion. [consulted: 13 of June of 2026]. Available at: https://hdl.handle.net/2445/217853

Export metadata

JSON - METS

Share record