Skip to main content
MathOverflow

Return to Question

Bumped by Community user
new information
Source Link
JYY
JYY
  • 133
  • 6

I have read some literature about the convergence rate of block coordinate descent. They all assume that the object function $f$ is Lipschitz continuous, is there any results for the convergence rate if $f$ is continuous and convex but not have Lipschitz gradient?

Update: Assume the function $f$ is smooth and block coordinate descent can find the minimum of $f$ successfully without getting stuck at some points.

I have read some literature about the convergence rate of block coordinate descent. They all assume that the object function $f$ is Lipschitz continuous, is there any results for the convergence rate if $f$ is continuous and convex but not have Lipschitz gradient?

I have read some literature about the convergence rate of block coordinate descent. They all assume that the object function $f$ is Lipschitz continuous, is there any results for the convergence rate if $f$ is continuous and convex but not have Lipschitz gradient?

Update: Assume the function $f$ is smooth and block coordinate descent can find the minimum of $f$ successfully without getting stuck at some points.

Source Link
JYY
JYY
  • 133
  • 6

Block coordinate descent convergence rate

I have read some literature about the convergence rate of block coordinate descent. They all assume that the object function $f$ is Lipschitz continuous, is there any results for the convergence rate if $f$ is continuous and convex but not have Lipschitz gradient?