Universality Patterns in the Training of Neural Networks
Presented at Microsoft Research Lab - India, Bengaluru, India, 2019
This work proposes and demonstrates a surprising pattern in the training of neural networks: there is a one to one relation between the values of any pair of losses (such as cross entropy, mean squared error,
This work was submited in the Deep Phenomena workshop of ICML 2019. The pdf of the work is available here.
