We introduce a simple and efficient algorithm for unconstrained zeroth-order stochastic convex bandits and prove its regret is at most $(1 + r/d)[d^{1.5} \sqrt{n} + d^3] polylog(n, d, r)$ where $n$ is the horizon, $d$ the dimension and $r$ is the radius of a known ball containing the minimiser of the loss.
翻译:我们为未受限制的零级孔雀强盗采用一种简单有效的算法,并证明其遗憾最多为$(1+ r/d)[d ⁇ 1.5}\sqrt{n}+ d ⁇ 3]多元(n, d, r)美元,其中一美元是地平线,一美元是维度,一美元是包含损失最小度的已知球的半径。