Skip to content

AI & ML · Optimization

Gradient descent

744 problems in this skill, each with a solver-verified answer key. Answers are checked the moment you submit — with a hint if you want one and a worked solution afterwards.

What the problems look like

A few statements from this skill. Answers, hints and worked solutions live in the practice session.

  1. Warm-up

    Consider the convex function f(x)=2(x−3)2f(x) = 2(x - 3)^{2}. Starting from x0=−4x_0 = -4, take one step of gradient descent with learning rate η=310\eta = \frac{3}{10} using the update rule x1=x0−ηf′(x0)x_1 = x_0 - \eta f'(x_0). Find x1x_1.

  2. Warm-up

    Consider the convex function f(x)=4(x−4)2f(x) = 4(x - 4)^{2}. Starting from x0=−6x_0 = -6, take one step of gradient descent with learning rate η=18\eta = \frac{1}{8} using the update rule x1=x0−ηf′(x0)x_1 = x_0 - \eta f'(x_0). Find x1x_1.

  3. Warm-up

    Consider the convex function f(x)=3(x−2)2f(x) = 3(x - 2)^{2}. Starting from x0=−1x_0 = -1, take one step of gradient descent with learning rate η=210\eta = \frac{2}{10} using the update rule x1=x0−ηf′(x0)x_1 = x_0 - \eta f'(x_0). Find x1x_1.

Problems shown under their original terms: Generated (template, solver-computed).

Practice this free, right now

Unlimited math practice is on the free plan — no card, no trial clock.

See every Optimization skill for ai & ml