Good question if Adam works consistently better than SGD (or SGD with momentum).
-
Also inclined to believe, as Ian says, that if you expect to get credit in accord with standard norms, it helps to participate yourself in those norms, eg:pic.twitter.com/ScfESB2I1b
It's frustrating how opaque academic norms are to outsiders - it's not like there's a manual of this stuff. And I'm sure I violate some ML community norms, as an outsider to that community. But I'd guess those norms are the obstacle here, not some animosity toward pdf or fastai
-
-
it's indeed frustrating - and tbh when researching the subject first thing i go to is arxiv... too many blogs are out there so some form of curation is key - by the way of recommendation or from folks i know from http://fast.ai or kaggle etc
-
It does make sense to some extent. There’s no barrier to writing blog posts, resulting in a lot of noise. OTOH, only people who are convinced their contributions are novel and worth the effort will jump through the hoops of putting it on arXiv. So it’s easier to trust the latter
- 6 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.