暂无分享,去创建一个
We consider a non-stationary sequential stochastic optimization problem, in which the underlying cost functions change over time under a variation budget constraint. We propose an $L_{p,q}$-variation functional to quantify the change, which captures local spatial and temporal variations of the sequence of functions. Under the $L_{p,q}$-variation functional constraint, we derive both upper and matching lower regret bounds for smooth and strongly convex function sequences, which generalize previous results in (Besbes et al., 2015). Our results reveal some surprising phenomena under this general variation functional, such as the curse of dimensionality of the function domain. The key technical novelties in our analysis include an affinity lemma that characterizes the distance of the minimizers of two convex functions with bounded $L_p$ difference, and a cubic spline based construction that attains matching lower bounds.
[1] Elad Hazan,et al. Competing in the Dark: An Efficient Algorithm for Bandit Linear Optimization , 2008, COLT.
[2] Elad Hazan,et al. Bandit Convex Optimization: Towards Tight Bounds , 2014, NIPS.
[3] Ambuj Tewari,et al. Improved Regret Guarantees for Online Smooth Convex Optimization with Bandit Feedback , 2011, AISTATS.