Computer Science Department
School of Computer Science, Carnegie Mellon University


Approximation Algorithms Going Online

Sham Kakade*, Adam Tauman Kalai**, Katrina Ligett

January 2007


Keywords: Approximation algorithms, regret minimization, online linear optimzation

In an online linear optimization problem, on each period t, an online algorithm chooses st Ēš S from a fixed (possibly infinite) set S of feasible decisions. Nature (who may be adversarial) chooses a weight vector wt ∈Rn, and the algorithm incurs cost c(st,wt), where c is a fixed cost function that is linear in the weight vector. In the full-information setting, the vector wt is then revealed to the algorithm, and in the bandit setting, only the cost experienced, c(st,wt), is revealed. The goal of the online algorithm is to perform nearly as well as the best fixed s ∈S in hindsight. Many repeated decision-making problems with weights fit naturally into this framework, such as online shortest-path, online TSP, online clustering, and online weighted set cover.

Previously, it was shown how to convert any efficient exact offline optimization algorithm for such a problem into an efficient online bandit algorithm in both the full-information and the bandit settings, with average cost nearly as good as that of the best fixed s ∈S in hindsight. However, in the case where the offline algorithm is an approximation algorithm with ratio α > 1, the previous approach only worked for special types of approximation algorithms.

We show how to convert any efficient offline α-approximation algorithm for a linear optimization problem into an efficient algorithm for the corresponding online problem, with average cost not much larger than α times that of the best s ∈S, in both the full-information and the bandit settings. Our main innovation is in the full-information setting: we combine Zinkevich's algorithm for convex optimization with a geometric transformation that can be applied to any approximation algorithm. In the bandit setting, standard techniques apply, except that a "Barycentric Spanner" for problem is also (provably) necessary as input.

Our algorithm can also be viewed as a method for playing a large repeated games, where one can only compute approximate best-responses, rather than best-responses.

19 pages

*Toyota Technological Institute at Chicago
**Georgia Institute of Technology

Return to: SCS Technical Report Collection
School of Computer Science

This page maintained by