|
|
|
|
|
|
by LolWolf
2199 days ago
|
|
|
> Yes, but we’re going to be restricted to O(L) final accuracy no matter what This is not, in general, true for smooth functions so long as L is small enough (you can reach arbitrary accuracy with GD if L is smaller than ~ the reciprocal of the Lipchitz constant of a differentiable objective function but it need not be arbitrarily small). |
|
|