A Stein Identity for q-Gaussians with Bounded Support
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912942050508800 |
|---|---|
| author | Sklaviadis, Sophia Moellenhoff, Thomas Martins, Andre F. T. Figueiredo, Mario A. T. Khan, Mohammad Emtiyaz |
| author_facet | Sklaviadis, Sophia Moellenhoff, Thomas Martins, Andre F. T. Figueiredo, Mario A. T. Khan, Mohammad Emtiyaz |
| contents | Stein's identity is a fundamental tool in machine learning with applications in generative models, stochastic optimization, and other problems involving gradients of expectations under Gaussian distributions. Less attention has been paid to problems with non-Gaussian expectations. Here, we consider the class of bounded-support $q$-Gaussians and derive a new Stein identity leading to gradient estimators which have nearly identical forms to the Gaussian ones, and which are similarly easy to implement. We do this by extending the previous results of Landsman, Vanduffel, and Yao (2013) to prove new Bonnet- and Price-type theorems for q-Gaussians. We also simplify their forms by using escort distributions. Our experiments show that bounded-support distributions can reduce the variance of gradient estimators, which can potentially be useful for Bayesian deep learning and sharpness-aware minimization. Overall, our work simplifies the application of Stein's identity for an important class of non-Gaussian distributions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03673 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Stein Identity for q-Gaussians with Bounded Support Sklaviadis, Sophia Moellenhoff, Thomas Martins, Andre F. T. Figueiredo, Mario A. T. Khan, Mohammad Emtiyaz Machine Learning Stein's identity is a fundamental tool in machine learning with applications in generative models, stochastic optimization, and other problems involving gradients of expectations under Gaussian distributions. Less attention has been paid to problems with non-Gaussian expectations. Here, we consider the class of bounded-support $q$-Gaussians and derive a new Stein identity leading to gradient estimators which have nearly identical forms to the Gaussian ones, and which are similarly easy to implement. We do this by extending the previous results of Landsman, Vanduffel, and Yao (2013) to prove new Bonnet- and Price-type theorems for q-Gaussians. We also simplify their forms by using escort distributions. Our experiments show that bounded-support distributions can reduce the variance of gradient estimators, which can potentially be useful for Bayesian deep learning and sharpness-aware minimization. Overall, our work simplifies the application of Stein's identity for an important class of non-Gaussian distributions. |
| title | A Stein Identity for q-Gaussians with Bounded Support |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.03673 |