Touring sampling with pushforward maps - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2024

Touring sampling with pushforward maps

Vivien Cabannes
  • Function : Author
  • PersonId : 1089863
Charles Arnal

Abstract

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.
Fichier principal
Vignette du fichier
Touring.pdf (432.09 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04471440 , version 1 (21-02-2024)

Licence

Attribution

Identifiers

Cite

Vivien Cabannes, Charles Arnal. Touring sampling with pushforward maps. ICASSP 2024 - International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea. ⟨10.48550/ARXIV.2311.13845⟩. ⟨hal-04471440⟩
26 View
61 Download

Altmetric

Share

Gmail Facebook X LinkedIn More