A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis
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_ | 1866915859170066432 |
|---|---|
| author | Qiu, Junwen Zeng, Ziyang Mei, Leilei Zhang, Junyu |
| author_facet | Qiu, Junwen Zeng, Ziyang Mei, Leilei Zhang, Junyu |
| contents | Existing convergence of distributed optimization methods in non-Euclidean geometries typically rely on kernel assumptions: (i) global Lipschitz smoothness and (ii) bi-convexity of the associated Bregman divergence function. Unfortunately, these conditions are violated by nearly all kernels used in practice, leaving a huge theory-practice gap. This work closes this gap by developing a unified analytical tool that guarantees convergence under mild conditions. Specifically, we introduce Hessian relative uniform continuity (HRUC), a regularity satisfied by nearly all standard kernels. Importantly, HRUC is closed under concatenation, positive scaling, composition, and various kernel combinations. Leveraging the geometric structure induced by HRUC, we derive convergence guarantees for mirror descent-based gradient tracking without imposing any restrictive assumptions. More broadly, our analysis techniques extend seamlessly to other decentralized optimization methods in genuinely non-Euclidean and non-Lipschitz settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12838 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis Qiu, Junwen Zeng, Ziyang Mei, Leilei Zhang, Junyu Optimization and Control Distributed, Parallel, and Cluster Computing Machine Learning 90C06, 90C30, 90C26 Existing convergence of distributed optimization methods in non-Euclidean geometries typically rely on kernel assumptions: (i) global Lipschitz smoothness and (ii) bi-convexity of the associated Bregman divergence function. Unfortunately, these conditions are violated by nearly all kernels used in practice, leaving a huge theory-practice gap. This work closes this gap by developing a unified analytical tool that guarantees convergence under mild conditions. Specifically, we introduce Hessian relative uniform continuity (HRUC), a regularity satisfied by nearly all standard kernels. Importantly, HRUC is closed under concatenation, positive scaling, composition, and various kernel combinations. Leveraging the geometric structure induced by HRUC, we derive convergence guarantees for mirror descent-based gradient tracking without imposing any restrictive assumptions. More broadly, our analysis techniques extend seamlessly to other decentralized optimization methods in genuinely non-Euclidean and non-Lipschitz settings. |
| title | A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis |
| topic | Optimization and Control Distributed, Parallel, and Cluster Computing Machine Learning 90C06, 90C30, 90C26 |
| url | https://arxiv.org/abs/2603.12838 |