Online optimization with switching cost

Abstract

We consider algorithms for "smoothed online convex optimization (SOCO)" problems. SOCO is a variant of the class of "online convex optimization (OCO)" problems that is strongly related to the class of "metrical task systems", each of which have been studied extensively. Prior literature on these problems has focused on two performance metrics: regret and competitive ratio. There exist known algorithms with sublinear regret and known algorithms with constant competitive ratios; however no known algorithms achieve both. In this paper, we show that this is due to a fundamental incompatibility between regret and the competitive ratio -- no algorithm (deterministic or randomized) can achieve sublinear regret and a constant competitive ratio, even in the case when the objective functions are linear.

Files

Additional details