Exercise · ZW-CONVERGENCE-WITH-LIPSCHITZ-GRADIENT-005 · ★☆☆ Basic
If \( \nabla f \) is Lipschitz, what does convexity of \( f \) add for the descent sequence?
Choose one option.
Show answer
- A. It allows bounding \( f(x_k)-f^* \) at rate \( O(1/k) \)
Exercise · ZW-CONVERGENCE-WITH-LIPSCHITZ-GRADIENT-005 · ★☆☆ Basic
Choose one option.
Convexity allows using the gradient inequality to obtain the \( O(1/k) \) bound. The other options contradict the basic results of the method.
Result guaranteeing that gradient descent with a suitable step size converges for differentiable functions whose gradient \( \nabla f \) is Lipschitz continuous with constant \( L \).
← ZW-CONVERGENCE-WITH-LIPSCHITZ-GRADIENT-004 ZW-CONVERGENCE-WITH-LIPSCHITZ-GRADIENT-006 →