Abstract
We study two randomized algorithms for generalized linear bandits, GLM-TSL and GLM-FPL. GLM-TSL samples a generalized linear model (GLM) from the Laplace approximation to the posterior distribution. GLM-FPL fits a GLM to a randomly perturbed history of past rewards. We prove C d (n log K)^(1/2) bounds (up to log factors) on the n-round regret of GLM-TSL and GLM-FPL, where d is the number of features and K is the number of arms. The regret bound of GLM-TSL improves upon prior work and the regret bound of GLM-FPL is the first of its kind. We apply both GLM-TSL and GLM-FPL to logistic and neural network bandits, and show that they perform well empirically. In more complex models, GLM-FPL is significantly faster. Our results showcase the role of randomization, beyond sampling from the posterior, in exploration.
Users
Please
log in to take part in the discussion (add own reviews or comments).