Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits

10/23/2020
by   Marc Abeille, et al.
0

Logistic Bandits have recently attracted substantial attention, by providing an uncluttered yet challenging framework for understanding the impact of non-linearity in parametrized bandits. It was shown by Faury et al. (2020) that the learning-theoretic difficulties of Logistic Bandits can be embodied by a large (sometimes prohibitively) problem-dependent constant κ, characterizing the magnitude of the reward's non-linearity. In this paper we introduce a novel algorithm for which we provide a refined analysis. This allows for a better characterization of the effect of non-linearity and yields improved problem-dependent guarantees. In most favorable cases this leads to a regret upper-bound scaling as 𝒪̃(d√(T/κ)), which dramatically improves over the 𝒪̃(d√(T)+κ) state-of-the-art guarantees. We prove that this rate is minimax-optimal by deriving a Ω(d√(T/κ)) problem-dependent lower-bound. Our analysis identifies two regimes (permanent and transitory) of the regret, which ultimately re-conciliates Faury et al. (2020) with the Bayesian approach of Dong et al. (2019). In contrast to previous works, we find that in the permanent regime non-linearity can dramatically ease the exploration-exploitation trade-off. While it also impacts the length of the transitory phase in a problem-dependent fashion, we show that this impact is mild in most reasonable configurations.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset