Differentiable optimization is a promising field of convex optimization and has many potential applications in game theory, control theory and machine learning. Unlike cvxpy, JuMP currently lacks the feature to differentiate solutions of disciplined convex optimization problems and render them as layers in machine learning libraries. I propose to develop this feature and make it accessible from the JuMP interface.

Organization

Student

AkshaySharma

Mentors

  • Joaquim
  • BenoĆ®t Legat
  • Mario Souto
close

2020