pith. sign in

arxiv: 1508.03769 · v1 · pith:QATMRBFYnew · submitted 2015-08-15 · 💻 cs.DS

A Tale of Two Metrics: Simultaneous Bounds on Competitiveness and Regret

classification 💻 cs.DS
keywords regretcompetitivealgorithmalgorithmsknownmetricsproblemsratio
0
0 comments X
read the original abstract

We consider algorithms for "smoothed online convex optimization" problems, a variant of the class of online convex optimization problems that is strongly related to metrical task systems. Prior literature on these problems has focused on two performance metrics: regret and the competitive ratio. There exist known algorithms with sublinear regret and known algorithms with constant competitive ratios; however, no known algorithm achieves both simultaneously. We show that this is due to a fundamental incompatibility between these two metrics - no algorithm (deterministic or randomized) can achieve sublinear regret and a constant competitive ratio, even in the case when the objective functions are linear. However, we also exhibit an algorithm that, for the important special case of one-dimensional decision spaces, provides sublinear regret while maintaining a competitive ratio that grows arbitrarily slowly.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.