Stein Discrepancy for Unsupervised Domain Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909946597081088 |
|---|---|
| author | von Seeger, Anneke Zou, Dongmian Lerman, Gilad |
| author_facet | von Seeger, Anneke Zou, Dongmian Lerman, Gilad |
| contents | Unsupervised domain adaptation (UDA) aims to improve model performance on an unlabeled target domain using a related, labeled source domain. A common approach aligns source and target feature distributions by minimizing a distance between them, often using symmetric measures such as maximum mean discrepancy (MMD). However, these methods struggle when target data is scarce. We propose a novel UDA framework that leverages Stein discrepancy, an asymmetric measure that depends on the target distribution only through its score function, making it particularly suitable for low-data target regimes. Our proposed method has kernelized and adversarial forms and supports flexible modeling of the target distribution via Gaussian, GMM, or VAE models. We derive a generalization bound on the target error and a convergence rate for the empirical Stein discrepancy in the two-sample setting. Empirically, our method consistently outperforms prior UDA approaches under limited target data across multiple benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03587 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stein Discrepancy for Unsupervised Domain Adaptation von Seeger, Anneke Zou, Dongmian Lerman, Gilad Machine Learning Unsupervised domain adaptation (UDA) aims to improve model performance on an unlabeled target domain using a related, labeled source domain. A common approach aligns source and target feature distributions by minimizing a distance between them, often using symmetric measures such as maximum mean discrepancy (MMD). However, these methods struggle when target data is scarce. We propose a novel UDA framework that leverages Stein discrepancy, an asymmetric measure that depends on the target distribution only through its score function, making it particularly suitable for low-data target regimes. Our proposed method has kernelized and adversarial forms and supports flexible modeling of the target distribution via Gaussian, GMM, or VAE models. We derive a generalization bound on the target error and a convergence rate for the empirical Stein discrepancy in the two-sample setting. Empirically, our method consistently outperforms prior UDA approaches under limited target data across multiple benchmarks. |
| title | Stein Discrepancy for Unsupervised Domain Adaptation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.03587 |