Technical Note—Nonstationary Stochastic Optimization UnderLp,q-Variation Measures
Xi Chen, Yining Wang, Yu-Xiang Wang
Operations Research · 2019 · Volume 67 · Issue 6
Abstract
We consider a nonstationary 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 yields less variation for dynamic function sequences whose changes are constrained to short time periods or small subsets of input domain. Under the L p,q -variation constraint, we derive both upper and matching lower regret bounds for smooth and strongly convex function sequences, which generalize previously published results [ Besbes O, Gur Y, Zeevi A (2015) Non-stationary stochastic optimization. Oper. Res . 63(5):1227–1244]. Furthermore, we provide an upper bound for general convex function sequences with noisy gradient feedback, which matches the optimal rate as p → ∞. Our results reveal some interesting phenomena under this general variation functional, such as the curse of dimensionality of the function domain. The key technical novelties in our analysis include affinity lemmas that characterize 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.
Keywords
analysis of algorithms, decision analysis: sequential, statistics: nonparametric, Stochastic Models, nonstationary stochastic optimization, bandit convex optimization, variation budget constraints, minimax regret
Enable JavaScript for citation tools and additional paper interactions.