Skip to yearly menu bar Skip to main content


Poster

Doubly-Robust Lasso Bandit

Gi-Soo Kim · Myunghee Cho Paik

East Exhibition Hall B, C #20

Keywords: [ Bandit Algorithms ] [ Algorithms ] [ Algorithms -> Adaptive Data Analysis; Algorithms -> Missing Data; Algorithms -> Online Learning; Algorithms ] [ Sparsity and Com ]


Abstract: Contextual multi-armed bandit algorithms are widely used in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health. Most of the existing algorithms have regret proportional to a polynomial function of the context dimension, $d$. In many applications however, it is often the case that contexts are high-dimensional with only a sparse subset of size $s_0 (\ll d)$ being correlated with the reward. We consider the stochastic linear contextual bandit problem and propose a novel algorithm, namely the Doubly-Robust Lasso Bandit algorithm, which exploits the sparse structure of the regression parameter as in Lasso, while blending the doubly-robust technique used in missing data literature. The high-probability upper bound of the regret incurred by the proposed algorithm does not depend on the number of arms and scales with $\mathrm{log}(d)$ instead of a polynomial function of $d$. The proposed algorithm shows good performance when contexts of different arms are correlated and requires less tuning parameters than existing methods.

Live content is unavailable. Log in and register to view live content