Efficiency of stochastic coordinate proximal gradient methods on nonseparable composite optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913189544853504 |
|---|---|
| author | Necoara, I. Chorobura, F. |
| author_facet | Necoara, I. Chorobura, F. |
| contents | This paper deals with composite optimization problems having the objective function formed as the sum of two terms, one has Lipschitz continuous gradient along random subspaces and may be nonconvex and the second term is simple and differentiable, but possibly nonconvex and nonseparable. Under these settings we design a stochastic coordinate proximal gradient method which takes into account the nonseparable composite form of the objective function. This algorithm achieves scalability by constructing at each iteration a local approximation model of the whole nonseparable objective function along a random subspace with user-determined dimension. We outline efficient techniques for selecting the random subspace, yielding an implementation that has low cost per-iteration while also achieving fast convergence rates. We present a probabilistic worst-case complexity analysis for our stochastic coordinate proximal gradient method in convex and nonconvex settings, in particular we prove high-probability bounds on the number of iterations before a given optimality is achieved. Extensive numerical results also confirm the efficiency of our algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2104_13370 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Efficiency of stochastic coordinate proximal gradient methods on nonseparable composite optimization Necoara, I. Chorobura, F. Optimization and Control This paper deals with composite optimization problems having the objective function formed as the sum of two terms, one has Lipschitz continuous gradient along random subspaces and may be nonconvex and the second term is simple and differentiable, but possibly nonconvex and nonseparable. Under these settings we design a stochastic coordinate proximal gradient method which takes into account the nonseparable composite form of the objective function. This algorithm achieves scalability by constructing at each iteration a local approximation model of the whole nonseparable objective function along a random subspace with user-determined dimension. We outline efficient techniques for selecting the random subspace, yielding an implementation that has low cost per-iteration while also achieving fast convergence rates. We present a probabilistic worst-case complexity analysis for our stochastic coordinate proximal gradient method in convex and nonconvex settings, in particular we prove high-probability bounds on the number of iterations before a given optimality is achieved. Extensive numerical results also confirm the efficiency of our algorithm. |
| title | Efficiency of stochastic coordinate proximal gradient methods on nonseparable composite optimization |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2104.13370 |