News for hackers. Stuff that matters.
Re:Evaluating the Search Phase of Neural Architecture Search by dchichkov on Friday November 22, 2019 @02:16AM (#21603524)
Should this be a cause to correct affected papers? If not corrected, maybe even retract?

I understand that there is still clear value in these papers (defining search space, achieving state of the art).

But it does seem, there is some partially broken science there (not evaluating against baselines, algorithm that performs same as a random baseline).

There are no comments on this comment yet.