DFWLayer: Differentiable Frank-Wolfe Optimization Layer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916183203119104 |
|---|---|
| author | Liu, Zixuan Liu, Liu Wang, Xueqian Zhao, Peilin |
| author_facet | Liu, Zixuan Liu, Liu Wang, Xueqian Zhao, Peilin |
| contents | Differentiable optimization has received a significant amount of attention due to its foundational role in the domain of machine learning based on neural networks. This paper proposes a differentiable layer, named Differentiable Frank-Wolfe Layer (DFWLayer), by rolling out the Frank-Wolfe method, a well-known optimization algorithm which can solve constrained optimization problems without projections and Hessian matrix computations, thus leading to an efficient way of dealing with large-scale convex optimization problems with norm constraints. Experimental results demonstrate that the DFWLayer not only attains competitive accuracy in solutions and gradients but also consistently adheres to constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_10806 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DFWLayer: Differentiable Frank-Wolfe Optimization Layer Liu, Zixuan Liu, Liu Wang, Xueqian Zhao, Peilin Machine Learning Artificial Intelligence Differentiable optimization has received a significant amount of attention due to its foundational role in the domain of machine learning based on neural networks. This paper proposes a differentiable layer, named Differentiable Frank-Wolfe Layer (DFWLayer), by rolling out the Frank-Wolfe method, a well-known optimization algorithm which can solve constrained optimization problems without projections and Hessian matrix computations, thus leading to an efficient way of dealing with large-scale convex optimization problems with norm constraints. Experimental results demonstrate that the DFWLayer not only attains competitive accuracy in solutions and gradients but also consistently adheres to constraints. |
| title | DFWLayer: Differentiable Frank-Wolfe Optimization Layer |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2308.10806 |