Bandits in Prod: Hyperparameter Optimization at Inference Time
This work introduces IMABO, a general framework that combines any bandit policy for choosing among already sampled configurations with any oracle for proposing new ones, and proves an expected cumulative quantile-regret bound of O(p_\rho^{-1/\beta} + T^{(1+\beta)/2})$.
L. Abraham, T. Nguyen, Nicolas Devatine
· 0 citations