Move from Perturbed scheme to exponential weighting average
Abstract
In an online decision problem, one makes decisions often with a pool of decision sequence called experts but without knowledge of the future. After each step, one pays a cost based on the decision and observed rate. One reasonal goal would be to perform as well as the best expert in the pool. The modern and wellknown way to attain this goal is the algorithm of exponential weighting. However, recently, another algorithm called follow the perturbed leader is developed and achieved about the same performance. In our work, we first show the properties shared in common by the two algorithms which explain the similarities on the performance. Next we will show that for a specific perturbation, the two algorithms are identical. Finally, we show with some examples that followtheleader style algorithms extend naturally to a large class of structured online problems for which the exponential algorithms are inefficient.
 Publication:

arXiv eprints
 Pub Date:
 December 2015
 arXiv:
 arXiv:1512.07074
 Bibcode:
 2015arXiv151207074X
 Keywords:

 Computer Science  Machine Learning
 EPrint:
 10 pages