Competitive algorithms for on-line problems
STOC '88 Proceedings of the twentieth annual ACM symposium on Theory of computing
An optimal on-line algorithm for metrical task system
Journal of the ACM (JACM)
Proceedings of the fifteenth annual ACM symposium on Parallel algorithms and architectures
Efficient algorithms for universal portfolios
FOCS '00 Proceedings of the 41st Annual Symposium on Foundations of Computer Science
Logarithmic regret algorithms for online convex optimization
Machine Learning
Randomized k-server on hierarchical binary trees
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
A decomposition theorem and bounds for randomized server problems
SFCS '92 Proceedings of the 33rd Annual Symposium on Foundations of Computer Science
Multi-armed Bandits with Metric Switching Costs
ICALP '09 Proceedings of the 36th Internatilonal Collogquium on Automata, Languages and Programming: Part II
Online algorithms for geographical load balancing
IGCC '12 Proceedings of the 2012 International Green Computing Conference (IGCC)
Hi-index | 0.00 |
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.