#linear-bandits

0 stories this week · 1 this month · 3 in 6 months · mostly AI

Stories per day · 30 days

3 stories, newest first · one card per story

For K actions in d dimensions it reaches Õ(√(dT log K)+dC) regret and settles the compact-set rate.

PC-LinUCB keeps a small persistent action set so linear bandits avoid scoring every arm each round.

A rare-switching bandit algorithm keeps exact sliding-window feasibility with near-optimal regret.

Stories tagged #linear-bandits