Predicting Nearly as Well as the Best Pruning of a Planar Decision Graph

摘要

We design efficient on-line algorihtms that predict nearly as well as the best pruning of a planar decision graph. We assume that the graph has no cycles. As in the previous work on decision trees, we implicitly maintain one weight for each of the prunings (exponentially many). The mehtod works for a large class of algorithms that update its weights multiplicatively. It can also be used to design algorithms that predict nearly as well as the best convex combination of prunings.