question for ML people out there:
is there any model/ optimizer/ algorithm out there (for any kind of ML task)
that will make your life much easier but it incredibly godawful slow to be worth considering practically?
is there any model/ optimizer/ algorithm out there (for any kind of ML task)
that will make your life much easier but it incredibly godawful slow to be worth considering practically?
Comments
what might be the thing that will make training easier but it is too slow for it to be worthwhile
any kind of simulation/ verification in the loop of training
second order optimizers (although that is being worked pretty close to being useful now)