A Time and Space Efficient Algorithm for Contextual Linear Bandits

We consider a multi-armed bandit problem where payoffs are a linear function of an observed stochastic contextual variable. In the scenario where there exists a gap between optimal and suboptimal rewards, several algorithms have been proposed that achieve O(log T ) regret after T time steps. However, proposed methods either have a computation complexity per iteration that scales linearly with T or achieve regrets that grow linearly with the number of contexts |X |. We propose an -greedy type of algorithm that solves both limitations. In particular, when contexts are variables in R, we prove that our algorithm has a constant computation complexity per iteration of O(poly(d)) and can achieve a regret ofO(poly(d) log T ) even when |X | = Ω(2). In addition, unlike previous algorithms, its space complexity scales like O(Kd) and does not grow with T .