cvxpylayers
A Python library for constructing differentiable convex optimization layers in PyTorch, JAX, and MLX using CVXPY.
What is cvxpylayers?
CVXPYlayers is a Python library that creates differentiable convex optimization layers for deep learning frameworks like PyTorch, JAX, and MLX. It allows developers to embed convex optimization problems as trainable components within neural networks, solving parametrized problems during forward passes and computing gradients during backward passes. This enables end-to-end learning of systems that require optimization-based reasoning or hard constraints.
Machine learning researchers and engineers working on models that incorporate optimization constraints, control systems, portfolio optimization, physics-informed learning, or any application requiring differentiable optimization layers within neural networks.
Developers choose CVXPYlayers because it provides a clean interface between CVXPY's expressive convex optimization modeling and popular deep learning frameworks, with GPU acceleration support and the ability to differentiate through complex optimization problems including log-log convex programs.
Overview
Differentiable convex optimization layers
Use Cases
Best For
- Embedding convex optimization constraints within neural network architectures
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
