Efficient Contextual Bandits in Non-stationary Worlds
This addresses the challenge of dynamic decision-making in applications like online advertising or recommendation systems where environments change over time, offering incremental improvements over prior work.
The paper tackles the problem of contextual bandits in non-stationary environments by developing efficient algorithms that adapt to distribution changes, achieving regret bounds such as O(√ST) with S stationary periods and O(Δ^{1/3}T^{2/3}) for a non-stationarity measure Δ, nearly matching optimal inefficient baselines.
Most contextual bandit algorithms minimize regret against the best fixed policy, a questionable benchmark for non-stationary environments that are ubiquitous in applications. In this work, we develop several efficient contextual bandit algorithms for non-stationary environments by equipping existing methods for i.i.d. problems with sophisticated statistical tests so as to dynamically adapt to a change in distribution. We analyze various standard notions of regret suited to non-stationary environments for these algorithms, including interval regret, switching regret, and dynamic regret. When competing with the best policy at each time, one of our algorithms achieves regret $\mathcal{O}(\sqrt{ST})$ if there are $T$ rounds with $S$ stationary periods, or more generally $\mathcal{O}(Δ^{1/3}T^{2/3})$ where $Δ$ is some non-stationarity measure. These results almost match the optimal guarantees achieved by an inefficient baseline that is a variant of the classic Exp4 algorithm. The dynamic regret result is also the first one for efficient and fully adversarial contextual bandit. Furthermore, while the results above require tuning a parameter based on the unknown quantity $S$ or $Δ$, we also develop a parameter free algorithm achieving regret $\min\{S^{1/4}T^{3/4}, Δ^{1/5}T^{4/5}\}$. This improves and generalizes the best existing result $Δ^{0.18}T^{0.82}$ by Karnin and Anava (2016) which only holds for the two-armed bandit problem.