2 problems

The time-varying bandit setting concerns sequential optimization problems in which the objective or reward function may change over time. Time-varying bandit extension conjecture.…

Let $n$ be the time horizon, $d$ the dimension, and let $\mathfrak{R}_n^\star$ denote the minimax regret for zeroth-order adversarial bandit convex optimisation. Bubeck–Lee–Eldan c…