Document type
Master thesisPublication date
Publication license
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
Authors
Director/Tutor
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
Subject (English)
Citation
Collections
Citation
PUJOL VIDAL, Àlex. Fundamental principles of Binary Latent Diffusion. [consulted: 13 of June of 2026]. Available at: https://hdl.handle.net/2445/217853