Product
cvxpylayers
cvxpylayers is a differentiable convex optimization layer library built on CVXPY. It allows convex optimization problems to be used as PyTorch or TensorFlow network layers, supports end-to-end gradient backpropagation, and is used to embed constraint-satisfying optimization steps within neural networks.
Timeline (last 90 days)
Oct 12
Representative frameworks for differentiable optimization layers are OptNet and cvxpylayers, which treat convex optimization problems as a layer in a neural network, with gradients back-propagated via the implicit function theorem or KKT conditions.
Unverified50%