Papers
Topics
Authors
Recent
Search
2000 character limit reached

DFWLayer: Differentiable Frank-Wolfe Optimization Layer

Published 21 Aug 2023 in cs.LG and cs.AI | (2308.10806v2)

Abstract: Differentiable optimization has received a significant amount of attention due to its foundational role in the domain of machine learning based on neural networks. This paper proposes a differentiable layer, named Differentiable Frank-Wolfe Layer (DFWLayer), by rolling out the Frank-Wolfe method, a well-known optimization algorithm which can solve constrained optimization problems without projections and Hessian matrix computations, thus leading to an efficient way of dealing with large-scale convex optimization problems with norm constraints. Experimental results demonstrate that the DFWLayer not only attains competitive accuracy in solutions and gradients but also consistently adheres to constraints.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (13)
  1. Differentiable convex optimization layers. Advances in neural information processing systems, 32, 2019.
  2. Optnet: Differentiable optimization as a layer in neural networks. In International Conference on Machine Learning, pp.  136–145. PMLR, 2017.
  3. Qplayer: efficient differentiation of convex quadratic optimization. Optimization, 2023.
  4. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine learning, 3(1):1–122, 2011.
  5. Conditional gradient methods. arXiv preprint arXiv:2211.14103, 2022.
  6. Openai gym, 2016.
  7. Learning with combinatorial optimization layers: a probabilistic approach. arXiv preprint arXiv:2207.13513, 2022.
  8. Dc3: A learning method for optimization with hard constraints. In International Conference on Learning Representations, 2020.
  9. Benjamin Ellenberger. Pybullet gymperium. https://github.com/benelot/pybullet-gym, 2018–2019.
  10. An algorithm for quadratic programming. Naval research logistics quarterly, 3(1-2):95–110, 1956.
  11. Benchmarking actor-critic deep reinforcement learning algorithms for robotics control with action constraints. IEEE Robotics and Automation Letters, 2023.
  12. Benoit Landry. Differentiable and Bilevel Optimization for Control in Robotics. Stanford University, 2021.
  13. Alternating differentiation for optimization layers. In The Eleventh International Conference on Learning Representations, 2022.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.