Byzantine-Robust Distributed Sparse Learning Revisited
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_ | 1866911680123895808 |
|---|---|
| author | Wang, Yuxuan Zhang, Lixin Li, Kangqiang |
| author_facet | Wang, Yuxuan Zhang, Lixin Li, Kangqiang |
| contents | We revisit Byzantine robust distributed estimation for high-dimensional sparse linear models. By combining local $\ell_1$-regularized robust estimation with robust aggregation at the server, the framework applies to pseudo-Huber regression, quantile regression, and sparse SVM. We show that the resulting estimators yield non-asymptotic guarantees and attain near-optimal statistical rates under mild conditions, while remaining communication-efficient. Simulations confirm strong robustness in estimation, support recovery and classification accuracy under various Byzantine attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13283 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Byzantine-Robust Distributed Sparse Learning Revisited Wang, Yuxuan Zhang, Lixin Li, Kangqiang Machine Learning Statistics Theory We revisit Byzantine robust distributed estimation for high-dimensional sparse linear models. By combining local $\ell_1$-regularized robust estimation with robust aggregation at the server, the framework applies to pseudo-Huber regression, quantile regression, and sparse SVM. We show that the resulting estimators yield non-asymptotic guarantees and attain near-optimal statistical rates under mild conditions, while remaining communication-efficient. Simulations confirm strong robustness in estimation, support recovery and classification accuracy under various Byzantine attacks. |
| title | Byzantine-Robust Distributed Sparse Learning Revisited |
| topic | Machine Learning Statistics Theory |
| url | https://arxiv.org/abs/2605.13283 |