Differentiation of Blackbox Combinatorial Solvers by Michal Rolínek (before connection lost)

Achieving fusion of deep learning with combinatorial algorithms promises transformative changes to artificial intelligence. One possible approach is to introduce combinatorial building blocks into neural networks. Such end-to-end architectures have the potential to tackle combinatorial problems on raw input data such as ensuring global consistency in multi-object tracking or route planning on maps in robotics. We present a method that implements an efficient backward pass through blackbox implementations of combinatorial solvers with linear objective functions. We provide both theoretical and experimental backing. In the talk, we will cover the description of the method including initial synthetic experiments (ICLR 2020 spotlight), as well as two follow-ups; one on rank-based loss functions (CVPR 2020 oral) and another regarding deep graph matching for keypoint correspondence.