A Wiener Process Perspective on Local Intrinsic Dimension Estimation Methods
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915074675834880 |
|---|---|
| author | Tempczyk, Piotr Garncarek, Łukasz Filipiak, Dominik Kurpisz, Adam |
| author_facet | Tempczyk, Piotr Garncarek, Łukasz Filipiak, Dominik Kurpisz, Adam |
| contents | Local intrinsic dimension (LID) estimation methods have received a lot of attention in recent years thanks to the progress in deep neural networks and generative modeling. In opposition to old non-parametric methods, new methods use generative models to approximate diffused dataset density to scale the methods to high-dimensional datasets (e.g. images). In this paper, we investigate the recent state-of-the-art parametric LID estimation methods from the perspective of the Wiener process. We explore how these methods behave when their assumptions are not met. We give an extended mathematical description of those methods and their error as a function of the probability density of the data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17125 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Wiener Process Perspective on Local Intrinsic Dimension Estimation Methods Tempczyk, Piotr Garncarek, Łukasz Filipiak, Dominik Kurpisz, Adam Machine Learning Local intrinsic dimension (LID) estimation methods have received a lot of attention in recent years thanks to the progress in deep neural networks and generative modeling. In opposition to old non-parametric methods, new methods use generative models to approximate diffused dataset density to scale the methods to high-dimensional datasets (e.g. images). In this paper, we investigate the recent state-of-the-art parametric LID estimation methods from the perspective of the Wiener process. We explore how these methods behave when their assumptions are not met. We give an extended mathematical description of those methods and their error as a function of the probability density of the data. |
| title | A Wiener Process Perspective on Local Intrinsic Dimension Estimation Methods |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.17125 |