Differentiation of Blackbox Combinatorial Solvers
ICLR 2020 (spotlight)
Authors: Marin Vlastelica*, Anselm Paulus*, Vít Musil, Georg Martius, Michal Rolínek
Embed blackbox combinatorial solvers into neural networks without any sacrifices! How to turn c++ code for solving e.g. travelling salesman into a differentiable NN building block. Mostly theoretical work with update rule resembling classical SVM-based methods but revamped to make good theoretical sense for deep learning. The start of #blackboxbackprop.
This paper was among the top rated papers at OpenReview for the entire ICLR 2020 conference.
Links: Arxiv OpenReview Github Blogpost ICLR (video)
Bridging discrete optimization with deep learning. Maybe highly optimized (nondifferentiable) solvers for combinatorial problems will become great again 😍.
— Michal Rolínek (@MichalRolinek) December 6, 2019
Differentiation of Blackbox Combinatorial Solvers https://t.co/YOzYOYhz20 pic.twitter.com/N9v6PprYGg