A Regularization Approach to Metrical Task Systems

We address the problem of constructing randomized online algorithms for the Metrical Task Systems (MTS) problem on a metric against an oblivious adversary. Restricting our attention to the class of "work-based" algorithms, we provide a framework for designing algorithms that uses the technique of regularization. For the case when is a uniform metric, we exhibit two algorithms that arise from this framework, and we prove a bound on the competitive ratio of each. We show that the second of these algorithms is ln n + O(log log n) competitive, which is the current state-of-the art for the uniform MTS problem.

• Type: Conference
• Year: 2010
• Where: ALT
• Authors: Jacob Abernethy, Peter L. Bartlett, Niv Buchbinder, Isabelle Stanton
• Keywords: Algorithms, ALT 2010, Machine Learning, Metrical Task Systems, Online Algorithms