Deep Conditional Measure Quantization
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909099756617728 |
|---|---|
| author | Turinici, Gabriel |
| author_facet | Turinici, Gabriel |
| contents | Quantization of a probability measure means representing it with a finite set of Dirac masses that approximates the input distribution well enough (in some metric space of probability measures). Various methods exists to do so, but the situation of quantizing a conditional law has been less explored. We propose a method, called DCMQ, involving a Huber-energy kernel-based approach coupled with a deep neural network architecture. The method is tested on several examples and obtains promising results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_06907 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Deep Conditional Measure Quantization Turinici, Gabriel Machine Learning Artificial Intelligence Probability Quantization of a probability measure means representing it with a finite set of Dirac masses that approximates the input distribution well enough (in some metric space of probability measures). Various methods exists to do so, but the situation of quantizing a conditional law has been less explored. We propose a method, called DCMQ, involving a Huber-energy kernel-based approach coupled with a deep neural network architecture. The method is tested on several examples and obtains promising results. |
| title | Deep Conditional Measure Quantization |
| topic | Machine Learning Artificial Intelligence Probability |
| url | https://arxiv.org/abs/2301.06907 |