Papers of the day   All papers

Differentiable Convex Optimization Layers

Comments

Akshay Agrawal: CVXPY is now differentiable. Try our PyTorch and TensorFlow layers using our package, cvxpylayers: https://github.com/cvxgrp/cvxpylayers (& see our NeurIPS paper for details http://web.stanford.edu/~boyd/papers/pdf/diff_cvxpy.pdf)

3 replies, 614 likes


Brandon Amos: Stoked to share a milestone project for all of us! #NeurIPS2019 paper with @akshaykagrawal, @ShaneBarratt, S. Boyd, S. Diamond, @zicokolter: Differentiable Convex Optimization Layers Paper: http://web.stanford.edu/~boyd/papers/pdf/diff_cvxpy.pdf Blog Post: https://locuslab.github.io/2019-10-28-cvxpylayers/ Repo: https://github.com/cvxgrp/cvxpylayers

5 replies, 316 likes


Brandon Amos ✈️ #NeurIPS2019: I'm at #NeurIPS2019! Get in touch if you want to talk about... derivatives. And check out our paper and poster on Weds evening: https://nips.cc/Conferences/2019/Schedule?showEvent=13991 (I'm also open to talking about things that are not derivatives)

1 replies, 92 likes


Jonathan Larkin: This seems like a big deal. One could embed a portfolio optimization as a layer inside a larger PyTorch nn model. Need to think about this...

1 replies, 24 likes


Akshay Agrawal: Slides: https://docs.google.com/presentation/d/1HZCKCY8aOzVf0ZNrdvZBcIThgncD3xxqYKtBh-TuVkk/edit?usp=sharing Software: https://github.com/cvxgrp/cvxpylayers NeurIPS 2019 paper: http://web.stanford.edu/~boyd/papers/pdf/diff_cvxpy.pdf This is joint work with many people! @brandondamos , @ShaneBarratt , Stephen Boyd, Steven Diamond, and @zicokolter (5/5)

0 replies, 9 likes


Krishna Murthy: This is really cool work!

0 replies, 6 likes


Content

Found on Oct 28 2019 at http://web.stanford.edu/~boyd/papers/pdf/diff_cvxpy.pdf

PDF content of a computer science paper: Differentiable Convex Optimization Layers