A Poisson Jump-driven SDE Approach to Distributed Gradient Descent with Sparse Communication
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912696142659584 |
|---|---|
| author | Weber, Marc Strachan, John Paul Ebenbauer, Christian |
| author_facet | Weber, Marc Strachan, John Paul Ebenbauer, Christian |
| contents | To bridge the gap between idealised communication models and the stochastic reality of networked systems, we introduce a framework for embedding asynchronous communication directly into algorithm dynamics using stochastic differential equations (SDE) driven by Poisson Jumps. We apply this communication-aware design to the continuous-time gradient flow, yielding a distributed algorithm where updates occur via sparse Poisson events. Our analysis establishes communication rate bounds for asymptotic stability and, crucially, a higher, yet sparse, rate that provably any desired exponential convergence performance slower than the nominal, centralized flow. These theoretical results, shown for unconstrained quadratic optimisation, are validated by a numerical simulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06379 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Poisson Jump-driven SDE Approach to Distributed Gradient Descent with Sparse Communication Weber, Marc Strachan, John Paul Ebenbauer, Christian Optimization and Control To bridge the gap between idealised communication models and the stochastic reality of networked systems, we introduce a framework for embedding asynchronous communication directly into algorithm dynamics using stochastic differential equations (SDE) driven by Poisson Jumps. We apply this communication-aware design to the continuous-time gradient flow, yielding a distributed algorithm where updates occur via sparse Poisson events. Our analysis establishes communication rate bounds for asymptotic stability and, crucially, a higher, yet sparse, rate that provably any desired exponential convergence performance slower than the nominal, centralized flow. These theoretical results, shown for unconstrained quadratic optimisation, are validated by a numerical simulation. |
| title | A Poisson Jump-driven SDE Approach to Distributed Gradient Descent with Sparse Communication |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2511.06379 |