Skip to content
ml-recall

#minibatch-sgd

2 questions from Optimization & Calculus

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Short answer

easyAI-checkedOptimization & Calculus

Per-example gradients are i.i.d. If you increase the minibatch size from 16 to 256, by what factor does the standard deviation of the minibatch gradient shrink?

a number