Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings
Discussion options

gdalle
Apr 23, 2024
Maintainer

Based on https://arxiv.org/abs/2307.13565

Features

Julia PyTorch JAX
Analytical differentiation DiffOpt, ImplicitDifferentiation jaxopt
Regularization InferOpt, DifferentiableFrankWolfe
Perturbation InferOpt PyEPO
Black box InferOpt PyEPO
Losses InferOpt PyEPO
Contrastive PyEPO
Specific problems InferOpt PyEPO

Ease of use

InferOpt PyEPO
Math prog JuMP Pyomo, Gurobipy, COPT
Arbitrary solvers Yes Yes
Solution caching No Yes
Deep learning Zygote PyTorch

Why Julia?

Find an example where it is essential to stay in the same language between optimizer and neural network:

  • JuMP is better than Pyomo
  • GPU-compatible combinatorial solver?

Sell modularity first with #110
You must be logged in to vote

Replies: 0 comments

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
💡
Ideas
Labels
None yet
1 participant
@gdalle
Morty Proxy This is a proxified and sanitized view of the page, visit original site.