Abstract: An efficient prediction of range aggregation based on dagger uses bundled range aggregation, which can be regarded as the simultaneous execution of a range aggregate query on multiple datasets, returning a result for each dataset. Bundled range aggregation, which is conceptually equivalent to running a range aggregate query separately on multiple datasets, returning the query result on each dataset. In particular, the queried datasets can be arbitrarily chosen from a large number (hundreds or even thousands) of candidate datasets. The challenge is to minimize the query cost no matter how many and which datasets are selected. We propose DAGGER (Dataset Aggregation), an iterative algorithm that trains a deterministic policy that achieves good performance guarantees under its induced distribution of states. we found that Dagger is more stable and learns faster, while being more robust with respect to the choice of learning rates and action costing. These advantages are more pronounced in the parameter-free versions of the algorithms which avoid stochastic cost estimates and need simpler expert policy definitions. Finally, we assessed the effect of the learning rate in complex structured prediction tasks in which mistaken predictions can inhibit imitation learning algorithms from exploring useful parts of the training data.
Keywords: Aggregation, range search, index, dagger.
Title: An Efficient Prediction of Range Aggregation Based On Dagger
Author: Anitha.J, Maheswari.D, MadanMohan.M
International Journal of Computer Science and Information Technology Research
ISSN 2348-1196 (print), ISSN 2348-120X (online)
Research Publish Journals
