FlexGP - Cloud-Based Ensemble Learning with Genetic Programming for Large Regression Problems

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@Article{journals/grid/VeeramachaneniA15,
  author =       "Kalyan Veeramachaneni and Ignacio Arnaldo and 
                 Owen Derby and Una-May O'Reilly",
  title =        "{FlexGP} - Cloud-Based Ensemble Learning with Genetic
                 Programming for Large Regression Problems",
  journal =      "Journal of Grid Computing",
  year =         "2015",
  number =       "3",
  volume =       "13",
  bibdate =      "2015-12-10",
  bibsource =    "DBLP,
                 http://dblp.uni-trier.de/db/journals/grid/grid13.html#VeeramachaneniA15",
  pages =        "391--407",
  keywords =     "genetic algorithms, genetic programming, MRGP, ARM,
                 gossip protocol, Matlab, NSGA-II, ANN, seeding, Cloud
                 computing, Ensemble learning, Symbolic regression",
  URL =          "http://dx.doi.org/10.1007/s10723-014-9320-9",
  DOI =          "doi:10.1007/s10723-014-9320-9",
  size =         "17 pages",
  abstract =     "We describe FlexGP, the first Genetic Programming
                 system to perform symbolic regression on large-scale
                 datasets on the cloud via massive data-parallel
                 ensemble learning. FlexGP provides a decentralized,
                 fault tolerant parallelization framework that runs many
                 copies of Multiple Regression Genetic Programming, a
                 sophisticated symbolic regression algorithm, on the
                 cloud. Each copy executes with a different sample of
                 the data and different parameters. The framework can
                 create a fused model or ensemble on demand as the
                 individual GP learners are evolving. We demonstrate our
                 framework by deploying 100 independent GP instances in
                 a massive data-parallel manner to learn from a dataset
                 composed of 515K exemplars and 90 features, and by
                 generating a competitive fused model in less than 10
                 minutes.",
  notes =        "DataModeler \cite{Friese:2012:dortmund} and Eureqa
                 \cite{Science09:Schmidt} Data Modeller, Eurequa,
                 embarrassingly parallel, LASSO, factor subsets,
                 NSGA-II,regularized linear regression, Vopal Wabbit,
                 million song dataset DynEq GP, producer effect",
}

Genetic Programming entries for Kalyan Veeramachaneni Ignacio Arnaldo Lucas Owen C Derby Una-May O'Reilly

Citations