[sdenton4]

https://openreview.net/forum?id=Sy8gdB9xx

"our experiments establish that state-of-the-art convolutional networks for image classification trained with stochastic gradient methods easily fit a random labeling of the training data. This phenomenon is qualitatively unaffected by explicit regularization, and occurs even if we replace the true images by completely unstructured random noise."

[r-zip]

What's your point? It's not clear at all from this post.