cooper icon indicating copy to clipboard operation
cooper copied to clipboard

A general-purpose, deep learning-first library for constrained optimization in PyTorch

Results 21 cooper issues
Sort by recently updated
recently updated
newest added

### CMP and CMPState - Converted CMPState into a dataclass for improved readability and maintainability. - Removed dual attributes from `LagrangianStore`. - Moved the `backward` method from CMPState to `LagrangianStore`....

## Enhancement To aid the understanding of this great library one could add a very simple example problem, a proposal is shown below. ## Motivation Currently, the optimization problem in...

enhancement

## Bug Hello, i have discovered your library recently and i am trying to use it for my research. While trying to solve a constrained minimization problem, i encountered an...

bug

Even after reading the classification tutorial, I did not fully understand when and how to use the `proxy_ineq_defect`. In my case, I am running a dynamics simulation given a set...

enhancement

## Enhancement When a dual restart is triggered, the dual variables are reset to their initial value 0. Nonetheless, the state of the primal and dual optimizer remains the same....

enhancement

Closes #54 ## Changes On the multipliers module we created a new class called [cooper.multipliers.MultiplierModel](https://github.com/IsitaRex/cooper/blob/ff3d9e27f0d42ffb64c907a4486f1a74f57d8910/cooper/multipliers/multiplier_model.py), which predicts the value of the Lagrange multipliers associated with the equality or inequality constraints...

enhancement

## Enhancement Implement the _extrapolation from the past_ algorithm (Popov, 1980). A good and modern source is Gidel et al. (2019). This is an algorithm for computing parameter updates similar...

enhancement

## Enhancement Implement a "Multiplier Model" in Cooper. This idea comes from the [paper](https://proceedings.neurips.cc/paper/2020/hash/62db9e3397c76207a687c360e0243317-Abstract.html) by Narasimhan et al. Instead of tracking the Lagrange Multipliers of a constrained optimization problem explicitly,...

enhancement

## Enhancement This PR #52 made significant changes to the structure of the code for constrained optimizers. However, this change has not been fully integrated into the docs.

documentation
enhancement