Salvato in:
Dettagli Bibliografici
Autori principali: Bondar, Vitalii, Babenko, Vira, Trembovetskyi, Roman, Korobeinyk, Yurii, Dzyuba, Viktoriya
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.17171
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913178380664832
author Bondar, Vitalii
Babenko, Vira
Trembovetskyi, Roman
Korobeinyk, Yurii
Dzyuba, Viktoriya
author_facet Bondar, Vitalii
Babenko, Vira
Trembovetskyi, Roman
Korobeinyk, Yurii
Dzyuba, Viktoriya
contents This paper introduces a unified theoretical perspective that views deep generative models as probability transformation functions. Despite the apparent differences in architecture and training methodologies among various types of generative models - autoencoders, autoregressive models, generative adversarial networks, normalizing flows, diffusion models, and flow matching - we demonstrate that they all fundamentally operate by transforming simple predefined distributions into complex target data distributions. This unifying perspective facilitates the transfer of methodological improvements between model architectures and provides a foundation for developing universal theoretical approaches, potentially leading to more efficient and effective generative modeling techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17171
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep generative models as the probability transformation functions
Bondar, Vitalii
Babenko, Vira
Trembovetskyi, Roman
Korobeinyk, Yurii
Dzyuba, Viktoriya
Machine Learning
68T07
This paper introduces a unified theoretical perspective that views deep generative models as probability transformation functions. Despite the apparent differences in architecture and training methodologies among various types of generative models - autoencoders, autoregressive models, generative adversarial networks, normalizing flows, diffusion models, and flow matching - we demonstrate that they all fundamentally operate by transforming simple predefined distributions into complex target data distributions. This unifying perspective facilitates the transfer of methodological improvements between model architectures and provides a foundation for developing universal theoretical approaches, potentially leading to more efficient and effective generative modeling techniques.
title Deep generative models as the probability transformation functions
topic Machine Learning
68T07
url https://arxiv.org/abs/2506.17171