Michal Rolínek presents Differentiation of Blackbox Combinatorial Solvers

On 2020-06-29 11:00:00 at G205, Karlovo náměstí 13, Praha 2
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.
Responsible person: Petr Pošík