Theoremadvanced
Convergence of gradient descent for smooth convex functions
Also called O(1/k) rate for gradient descent.
With step 1/L, f(x_k) - f* is at most O(1/k) for L-smooth convex f.
With step 1/L, f(x_k) - f* is at most O(1/k) for L-smooth convex f.
About this page
The build computes these levels from the evidence in the repository. Each row says what the next level needs. Read what the levels mean.
| Ladder | Level | What the next level needs |
|---|---|---|
| Human proof | H0 no proof |
|
| Lean | L0 no Lean part |
|
| Visual | V0 none |
|
| Writing | W0 stub |
|
Tag NDY404 Edit this page History Report an error