Variance-Dependent Regret Bounds for Non-stationary Linear Bandits

arXiv:2403.10732v1 Announce Type: new
Abstract: We investigate the non-stationary stochastic linear bandit problem where the reward distribution evolves each round. Existing algorithms characterize the non-stationarity by the total variation budget $B_K$, which is the summation of the change of the consecutive feature vectors of the linear bandits over $K$ rounds. However, such a quantity only measures the non-stationarity with respect to the expectation of the reward distribution, which makes existing algorithms sub-optimal under the general non-stationary distribution setting. In this …

abstract algorithms arxiv budget change cs.ai cs.lg distribution feature however linear stochastic total type variance variation vectors