Last week we looked at the information bottleneck theory of DNNs. This ICLR'18 submission provides a critical analysis - turns out the choice of activation function has/had a lot to do with it!http://blog.acolyer.org/2017/11/24/on-the-information-bottleneck-theory-of-deep-learning …
-
-
AFAICT It's an open review system so the results are freely available for anyone to see. https://openreview.net/forum?id=ry_WPG-A …-
-
Thanks, I had no idea. This seems bizarre to me but I guess not others.
-
It takes a while to get your head around I agree! Submissions are open, and the review comments and discussion are open, but through that whole process the identity of the authors and reviewers remains hidden. http://www.iclr.cc/doku.php?id=iclr2018:conference_cfp …
-
It's surprising because open everything without an author name nor DOI makes me think credit can't be (easily) attributed to the authors neither via e.g., Google scholar (cites, for the REF, etc.) nor altmetrics (blogs about their work, Mendelay adds, tweets, etc).
-
Also unlike with preprints, which have names and DOIs or some ID (arXiv), the public PDF on this setup has neither an ID nor author names. It's open to abuse, if understand it correctly since I can see malevolent actors as well as just mistakes leading to copying anonymous' work.
-
I suppose it's not being abused since it's still in use. But open at the time of commenting and double blinding seems a strange combination to me, for the reasons I just mentioned.
-
I also noticed they allow preprints. What's the point of double blind if they allow preprints? If the point is to make it a level playing field then obviously a lab with a good reputation will "unlevel" the playing field by unanonymising themselves with a preprint.
-
Anyway, it's just my thoughts on this since I've never seen this combination of open at the time of review and double blind. Thanks for explaining it. If I ever submit to such a conference I'll be prepared!

- 3 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.