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 δ 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 δ 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.

[1]  Yuval Peres,et al.  Mixing Time Power Laws at Criticality , 2007, 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07).

[2]  Joseph Naor,et al.  A primal-dual randomized algorithm for weighted paging , 2007, 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07).

[3]  Yair Bartal,et al.  On approximating arbitrary metrices by tree metrics , 1998, STOC '98.

[4]  Joseph Naor,et al.  The Design of Competitive Online Algorithms via a Primal-Dual Approach , 2009, Found. Trends Theor. Comput. Sci..

[5]  Alexander Rakhlin,et al.  Lecture Notes on Online Learning DRAFT , 2009 .

[6]  Béla Bollobás,et al.  A Ramsey-type theorem for metric spaces and its applications for metrical task systems and related problems , 2001, Proceedings 2001 IEEE International Conference on Cluster Computing.

[7]  Geoffrey J. Gordon Regret bounds for prediction problems , 1999, COLT '99.

[8]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[9]  Joseph Naor,et al.  Metrical Task Systems and the k-Server Problem on HSTs , 2010, ICALP.

[10]  Lawrence L. Larmore,et al.  Uniform metrical task systems with a limited number of states , 2007, Inf. Process. Lett..

[11]  Yuval Rabani,et al.  A Decomposition Theorem for Task Systems and Bounds for Randomized Server Problems , 2000, SIAM J. Comput..

[12]  Joseph Naor,et al.  Towards the randomized k-server conjecture: a primal-dual approach , 2010, SODA '10.

[13]  Naveen Sivadasan,et al.  Topology matters: Smoothed competitiveness of metrical task systems , 2004, Theor. Comput. Sci..

[14]  Manfred K. Warmuth,et al.  Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..

[15]  Amos Fiat,et al.  Better algorithms for unfair metrical task systems and applications , 2000, STOC '00.

[16]  Andrew Tomkins,et al.  A polylog(n)-competitive algorithm for metrical task systems , 1997, STOC '97.

[17]  Avrim Blum,et al.  On-line Learning and the Metrical Task System Problem , 1997, COLT '97.

[18]  Mark Herbster,et al.  Tracking the Best Expert , 1995, Machine Learning.

[19]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[20]  Allan Borodin,et al.  An optimal on-line algorithm for metrical task system , 1992, JACM.

[21]  Lyle A. McGeoch,et al.  Competitive Algorithms for Server Problems , 1990, J. Algorithms.

[22]  Satish Rao,et al.  A tight bound on approximating arbitrary metrics by tree metrics , 2003, STOC '03.

[23]  Sandy Irani,et al.  Randomized Algorithms for Metrical Task Systems , 1998, Theor. Comput. Sci..