(Deep) Generative Geodesics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916325890195456 |
|---|---|
| author | Kim, Beomsu Puthawala, Michael Ye, Jong Chul Sansone, Emanuele |
| author_facet | Kim, Beomsu Puthawala, Michael Ye, Jong Chul Sansone, Emanuele |
| contents | In this work, we propose to study the global geometrical properties of generative models. We introduce a new Riemannian metric to assess the similarity between any two data points. Importantly, our metric is agnostic to the parametrization of the generative model and requires only the evaluation of its data likelihood. Moreover, the metric leads to the conceptual definition of generative distances and generative geodesics, whose computation can be done efficiently in the data space. Their approximations are proven to converge to their true values under mild conditions. We showcase three proof-of-concept applications of this global metric, including clustering, data visualization, and data interpolation, thus providing new tools to support the geometrical understanding of generative models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11244 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | (Deep) Generative Geodesics Kim, Beomsu Puthawala, Michael Ye, Jong Chul Sansone, Emanuele Machine Learning In this work, we propose to study the global geometrical properties of generative models. We introduce a new Riemannian metric to assess the similarity between any two data points. Importantly, our metric is agnostic to the parametrization of the generative model and requires only the evaluation of its data likelihood. Moreover, the metric leads to the conceptual definition of generative distances and generative geodesics, whose computation can be done efficiently in the data space. Their approximations are proven to converge to their true values under mild conditions. We showcase three proof-of-concept applications of this global metric, including clustering, data visualization, and data interpolation, thus providing new tools to support the geometrical understanding of generative models. |
| title | (Deep) Generative Geodesics |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2407.11244 |