%0 Journal Article %1 ji2017asymptotically %A Ji, Shiyu %A Wan, Kun %D 2017 %K bounds generalization learning theory %T An Asymptotically Tighter Bound on Sampling for Frequent Itemsets Mining %U http://arxiv.org/abs/1703.08273 %X In this paper we present a new error bound on sampling algorithms for frequent itemsets mining. We show that the new bound is asymptotically tighter than the state-of-art bounds, i.e., given the chosen samples, for small enough error probability, the new error bound is roughly half of the existing bounds. Based on the new bound, we give a new approximation algorithm, which is much simpler compared to the existing approximation algorithms, but can also guarantee the worst approximation error with precomputed sample size. We also give an algorithm which can approximate the top-$k$ frequent itemsets with high accuracy and efficiency.

@article{ji2017asymptotically, abstract = {In this paper we present a new error bound on sampling algorithms for frequent itemsets mining. We show that the new bound is asymptotically tighter than the state-of-art bounds, i.e., given the chosen samples, for small enough error probability, the new error bound is roughly half of the existing bounds. Based on the new bound, we give a new approximation algorithm, which is much simpler compared to the existing approximation algorithms, but can also guarantee the worst approximation error with precomputed sample size. We also give an algorithm which can approximate the top-$k$ frequent itemsets with high accuracy and efficiency.}, added-at = {2019-08-12T18:45:44.000+0200}, author = {Ji, Shiyu and Wan, Kun}, biburl = {https://www.bibsonomy.org/bibtex/239e44296b428e0891857c20201339ccc/kirk86}, description = {[1703.08273] An Asymptotically Tighter Bound on Sampling for Frequent Itemsets Mining}, interhash = {5c47c58f05c9ac7884bb8ada886a9740}, intrahash = {39e44296b428e0891857c20201339ccc}, keywords = {bounds generalization learning theory}, note = {cite arxiv:1703.08273Comment: 13 pages, 2 figures, 2 tables}, timestamp = {2019-08-12T18:45:44.000+0200}, title = {An Asymptotically Tighter Bound on Sampling for Frequent Itemsets Mining}, url = {http://arxiv.org/abs/1703.08273}, year = 2017 }