I find this super interesting but unfortunately don't have enough background in Deep Learning to recognise what this would be used for. To train a model that knows how to sort stuff (probably not)? Would someone have mercy and ELI5?
Deep learning models require that all of their component are differentiable in order to fit their parameters.
This means that most building blocks for neural networks are basic linear algebra and not much else (I am simplifying, nowadays we have access to a surprisingly large array of operations).
This paper gives you two new building block, a sorting function and a ranking function.
The ranking function might have direct applications for recommender systems.
