I am reading a recent paper "Generalization in Deep Learning" and I am unable to understand a step. In this step, they first take neural network as a direct acyclic graph(DAG) and described output of neural network as follows,

enter image description here

and then they decomposed generalization gap as follows,

enter image description here

without any explanation. Here z is,

enter image description here

Can someone explain this or point me towards the right direction.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.