Skip to content
ml-recall

#regret-bound

1 question from Multi-Agent Systems

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Single choice

hardAI-checkedMulti-Agent Systems

The negative entropy is 1-strongly convex on the simplex with respect to both the ℓ2\ell_2 and the ℓ1\ell_1 norm. The regret bound of (optimistic) multiplicative weights involves the strong-convexity norm and its dual norm applied to the utility vectors. Which choice gives the stronger bound?

Choose one option