Exercise · ZW-CONVERGENCE-WITH-LIPSCHITZ-GRADIENT-003 · ★☆☆ Basic

What is the function-value convergence rate for convex gradient descent with step \( 1/L \)?

Choose one option.

Show answer
  • C. \( O(1/k) \)

Explanation

With a Lipschitz gradient and a convex function, gradient descent converges at rate \( O(1/k) \). The option \( O(1/k^2) \) corresponds to accelerated methods, not plain descent.

Study Continuous optimization in ZWMath →

Review the concept: Convergence with Lipschitz gradient

Result guaranteeing that gradient descent with a suitable step size converges for differentiable functions whose gradient \( \nabla f \) is Lipschitz continuous with constant \( L \).

\[f(x_k)-f^* \le \frac{L\|x_0-x^*\|^2}{2k}\]

More practice problems: convergence with lipschitz gradient

← ZW-CONVERGENCE-WITH-LIPSCHITZ-GRADIENT-002 ZW-CONVERGENCE-WITH-LIPSCHITZ-GRADIENT-004 →