Stochastic Block Bregman Projection with Polyak-like Stepsize for Possibly Inconsistent Convex Feasibility Problems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912990650957824 |
|---|---|
| author | Zhang, Lu Chen, Hongzhen Wang, Hongxia Zhang, Hui |
| author_facet | Zhang, Lu Chen, Hongzhen Wang, Hongxia Zhang, Hui |
| contents | Stochastic projection algorithms for solving convex feasibility problems (CFPs) have attracted considerable attention due to their broad applicability. In this paper, we propose a unified stochastic bilevel reformulation for possibly inconsistent CFPs that combines proximity function minimization and structural regularization, leading to a feasible bilevel model with a unique and stable regularized solution. From the algorithmic perspective, we develop the stochastic block Bregman projection method with Polyak-like and projective stepsizes, which not only subsumes several recent stochastic projection algorithms but also induces new schemes tailored to specific problems. Moreover, we establish ergodic sublinear convergence rates for the expected inner function, as well as linear convergence in expectation to the inner minimizer set under a Bregman distance growth condition. In particular, the proposed Polyak-like stepsize ensures exact convergence in expectation for possibly inconsistent CFPs. Finally, numerical experiments demonstrate the effectiveness of the proposed method and its robustness to noise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29348 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stochastic Block Bregman Projection with Polyak-like Stepsize for Possibly Inconsistent Convex Feasibility Problems Zhang, Lu Chen, Hongzhen Wang, Hongxia Zhang, Hui Optimization and Control 90C25, 90C15, 65K05 Stochastic projection algorithms for solving convex feasibility problems (CFPs) have attracted considerable attention due to their broad applicability. In this paper, we propose a unified stochastic bilevel reformulation for possibly inconsistent CFPs that combines proximity function minimization and structural regularization, leading to a feasible bilevel model with a unique and stable regularized solution. From the algorithmic perspective, we develop the stochastic block Bregman projection method with Polyak-like and projective stepsizes, which not only subsumes several recent stochastic projection algorithms but also induces new schemes tailored to specific problems. Moreover, we establish ergodic sublinear convergence rates for the expected inner function, as well as linear convergence in expectation to the inner minimizer set under a Bregman distance growth condition. In particular, the proposed Polyak-like stepsize ensures exact convergence in expectation for possibly inconsistent CFPs. Finally, numerical experiments demonstrate the effectiveness of the proposed method and its robustness to noise. |
| title | Stochastic Block Bregman Projection with Polyak-like Stepsize for Possibly Inconsistent Convex Feasibility Problems |
| topic | Optimization and Control 90C25, 90C15, 65K05 |
| url | https://arxiv.org/abs/2603.29348 |