You are here

Non-stationary Stochastic Optimization

Non-stationary Stochastic Optimization

Coauthor(s): O. Besbes, Y. Gur, and A. Zeevi
Download (PDF)

We consider a non-stationary variant of a sequential stochastic optimization problem, where the underlying cost functions may change along the horizon. We propose a measure, termed variation budget, that controls the extent of said change, and study how restrictions on this budget impact achievable performance. We identify sharp conditions under which it is possible to achieve long-run-average optimality and more refi ned performance measures such as rate optimality that fully characterize the complexity of such problems. In doing so, we also establish a strong connection between two rather disparate strands of literature: adversarial online convex optimization; and the more traditional stochastic approximation paradigm (couched in a non-stationary setting). This connection is the key to deriving well performing policies in the latter, by leveraging structure of optimal policies in the former. Finally, tight bounds on the minimax regret allow us to quantify the "price of non-stationarity," which mathematically captures the added complexity embedded in a temporally changing environment versus a stationary one.

Exact Citation:
O. Besbes, Y. Gur, and A. Zeevi "Non-stationary Stochastic Optimization." , Columbia Business School, (2013).
Date: 2013