Touring sampling with pushforward maps

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cabannes, Vivien, Arnal, Charles
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913237877915648
author Cabannes, Vivien
Arnal, Charles
author_facet Cabannes, Vivien
Arnal, Charles
contents The number of sampling methods could be daunting for a practitioner looking to cast powerful machine learning methods to their specific problem. This paper takes a theoretical stance to review and organize many sampling approaches in the ``generative modeling'' setting, where one wants to generate new data that are similar to some training examples. By revealing links between existing methods, it might prove useful to overcome some of the current challenges in sampling with diffusion models, such as long inference time due to diffusion simulation, or the lack of diversity in generated samples.
format Preprint
id arxiv_https___arxiv_org_abs_2311_13845
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Touring sampling with pushforward maps
Cabannes, Vivien
Arnal, Charles
Machine Learning
Artificial Intelligence
The number of sampling methods could be daunting for a practitioner looking to cast powerful machine learning methods to their specific problem. This paper takes a theoretical stance to review and organize many sampling approaches in the ``generative modeling'' setting, where one wants to generate new data that are similar to some training examples. By revealing links between existing methods, it might prove useful to overcome some of the current challenges in sampling with diffusion models, such as long inference time due to diffusion simulation, or the lack of diversity in generated samples.
title Touring sampling with pushforward maps
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2311.13845