News for hackers. Stuff that matters.
Re:Generalization in Deep Learning [pdf] by amelius on Tuesday October 17, 2017 @05:52AM (#15489734)
> how long does it take you to read one paper?

It depends on to what extent the paper is self-contained.

Re:Generalization in Deep Learning [pdf] by benrbray on Tuesday October 17, 2017 @11:26AM (#15491715)
By applying Lemma 4.9 of Lee 2014 to Corollary 6.2.11 of Simpson 1954, but substituting Tao 1977's simplified integral expression in the denominator, the result is obvious.