Saved in:
Bibliographic Details
Main Authors: Korrapati, Jathin, Baranwal, Tanish, Shah, Rahul
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.19114
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913627455356928
author Korrapati, Jathin
Baranwal, Tanish
Shah, Rahul
author_facet Korrapati, Jathin
Baranwal, Tanish
Shah, Rahul
contents This work explores the theoretical and practical foundations of denoising diffusion probabilistic models (DDPMs) and score-based generative models, which leverage stochastic processes and Brownian motion to model complex data distributions. These models employ forward and reverse diffusion processes defined through stochastic differential equations (SDEs) to iteratively add and remove noise, enabling high-quality data generation. By analyzing the performance bounds of these models, we demonstrate how score estimation errors propagate through the reverse process and bound the total variation distance using discrete Girsanov transformations, Pinsker's inequality, and the data processing inequality (DPI) for an information theoretic lens.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19114
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Discrete vs. Continuous Trade-offs for Generative Models
Korrapati, Jathin
Baranwal, Tanish
Shah, Rahul
Machine Learning
Artificial Intelligence
Information Theory
Numerical Analysis
Primary 68T07, Secondary 60H10, 94A15, 68Q87
This work explores the theoretical and practical foundations of denoising diffusion probabilistic models (DDPMs) and score-based generative models, which leverage stochastic processes and Brownian motion to model complex data distributions. These models employ forward and reverse diffusion processes defined through stochastic differential equations (SDEs) to iteratively add and remove noise, enabling high-quality data generation. By analyzing the performance bounds of these models, we demonstrate how score estimation errors propagate through the reverse process and bound the total variation distance using discrete Girsanov transformations, Pinsker's inequality, and the data processing inequality (DPI) for an information theoretic lens.
title Discrete vs. Continuous Trade-offs for Generative Models
topic Machine Learning
Artificial Intelligence
Information Theory
Numerical Analysis
Primary 68T07, Secondary 60H10, 94A15, 68Q87
url https://arxiv.org/abs/2412.19114