Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
blackbear_
on Oct 20, 2020
|
parent
|
context
|
favorite
| on:
Why deep learning works even though it shouldn’t
Your intuition is off, but only slightly. As the dimensionality increases, the number of stationary points (zero gradient) also increases. But they become overwhelmingly likely to be saddle points rather than minima.
You can read more here [1].
[1]
http://ganguli-gang.stanford.edu/pdf/14.SaddlePoint.NIPS.pdf
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
You can read more here [1].
[1] http://ganguli-gang.stanford.edu/pdf/14.SaddlePoint.NIPS.pdf