Journal of Algorithms
An optimal on-line algorithm for metrical task system
Journal of the ACM (JACM)
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Approximate methods for sequential decision making using expert advice
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
The weighted majority algorithm
Information and Computation
A polylog(n)-competitive algorithm for metrical task systems
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
A decision-theoretic generalization of on-line learning and an application to boosting
Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Randomized algorithms for metrical task systems
Theoretical Computer Science
Unfair problems and randomized algorithms for metrical task systems
Information and Computation
Machine Learning - Special issue on context sensitivity and concept drift
On-line choice of on-line algorithms
SODA '93 Proceedings of the fourth annual ACM-SIAM Symposium on Discrete algorithms
Probabilistic approximation of metric spaces and its algorithmic applications
FOCS '96 Proceedings of the 37th Annual Symposium on Foundations of Computer Science
Static optimality and dynamic search-optimality in lists and trees
SODA '02 Proceedings of the thirteenth annual ACM-SIAM symposium on Discrete algorithms
Online algorithms for market clearing
SODA '02 Proceedings of the thirteenth annual ACM-SIAM symposium on Discrete algorithms
Learning Additive Models Online with Fast Evaluating Kernels
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Tracking Linear-Threshold Concepts with Winnow
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
Tracking the best linear predictor
The Journal of Machine Learning Research
Tracking linear-threshold concepts with Winnow
The Journal of Machine Learning Research
Online algorithms for market clearing
Journal of the ACM (JACM)
Dynamic coprocessor management for FPGA-enhanced compute platforms
CASES '08 Proceedings of the 2008 international conference on Compilers, architectures and synthesis for embedded systems
Dynamic tuning of configurable architectures: the AWW online algorithm
CODES+ISSS '08 Proceedings of the 6th IEEE/ACM/IFIP international conference on Hardware/Software codesign and system synthesis
Optimal Task Migration in Service-Oriented Systems: Algorithms and Mechanisms
Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
Metrical task systems and the k-server problem on HSTs
ICALP'10 Proceedings of the 37th international colloquium conference on Automata, languages and programming
A regularization approach to metrical task systems
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
Modeling long-term search engine usage
UMAP'10 Proceedings of the 18th international conference on User Modeling, Adaptation, and Personalization
Linear programming with online learning
Operations Research Letters
A tale of two metrics: simultaneous bounds on competitiveness and regret
Proceedings of the ACM SIGMETRICS/international conference on Measurement and modeling of computer systems
| Hi-index | 0.00 |
The problem ofcombining expert advice, studied extensively in theComputational Learning Theory literature, and the Metrical TaskSystem (MTS) problem,studied extensively in the area of On-line Algorithms,contain a number of interesting similarities. In this paper weexplore the relationship between these problems andshow how algorithms designed for each can be used to achievegood bounds and new approaches for solving the other.Specific contributions of this paper include:• An analysis of how two recent algorithms for the MTSproblem can beapplied to the problem of tracking the best expert in the“decision-theoretic” setting, providing goodbounds and an approach of a much different flavor fromthe well-known multiplicative-update algorithms.• An analysis showing how the standard randomized WeightedMajority (or Hedge) algorithm can be used for the problem of“combining on-line algorithms on-line”, giving much strongerguarantees than the results of Azar, Y., Broder, A., & Manasse, M. (1993).Proc ACM-SIAM Symposium on Discrete Algorithms (pp. 432–440)when the algorithms being combinedoccupy a state space of bounded diameter.• A generalization of the above, showing how (a simplified versionof) Herbster and Warmuth's weight-sharing algorithm can be applied togive a “finely competitive” bound for the uniform-spaceMetrical Task System problem.We also give a new, simpler algorithm for tracking experts, whichunfortunately does not carry over to the MTS problem.Finally, we present an experimental comparison of how these algorithmsperform on a process migration problem, a problem that combinesaspects of both the experts-tracking and MTS formalisms.