A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908448442023936 |
|---|---|
| author | Ryu, J. Jon Shah, Abhin Wornell, Gregory W. |
| author_facet | Ryu, J. Jon Shah, Abhin Wornell, Gregory W. |
| contents | This paper studies a family of estimators based on noise-contrastive estimation (NCE) for learning unnormalized distributions. The main contribution of this work is to provide a unified perspective on various methods for learning unnormalized distributions, which have been independently proposed and studied in separate research communities, through the lens of NCE. This unified view offers new insights into existing estimators. Specifically, for exponential families, we establish the finite-sample convergence rates of the proposed estimators under a set of regularity assumptions, most of which are new. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18209 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation Ryu, J. Jon Shah, Abhin Wornell, Gregory W. Machine Learning Statistics Theory This paper studies a family of estimators based on noise-contrastive estimation (NCE) for learning unnormalized distributions. The main contribution of this work is to provide a unified perspective on various methods for learning unnormalized distributions, which have been independently proposed and studied in separate research communities, through the lens of NCE. This unified view offers new insights into existing estimators. Specifically, for exponential families, we establish the finite-sample convergence rates of the proposed estimators under a set of regularity assumptions, most of which are new. |
| title | A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation |
| topic | Machine Learning Statistics Theory |
| url | https://arxiv.org/abs/2409.18209 |