Model and Algorithm Selection in Statistical Learning and Optimization
Created by W.Langdon from
gpbibliography.bib Revision:1.7416
 @PhdThesis{Bischl:thesis,

author = "Bernd Bischl",

title = "Model and Algorithm Selection in Statistical Learning
and Optimization",

school = "Fakultaet Statistik, Technische Universitaet
Dortmund",

year = "2014",

address = "Germany",

month = "7 " # feb,

keywords = "genetic algorithms, genetic programming, SVM, model
selection, algorithm selection, algorithm
configuration, tuning, benchmarking, machine learning",

URL = "https://eldorado.tudortmund.de/bitstream/2003/32861/1/phd.pdf",

URL = "http://hdl.handle.net/2003/32861",

URL = "https://eldorado.tudortmund.de/handle/2003/32861",

DOI = "doi:10.17877/DE290R7142",

size = "37 pages",

abstract = "Modern datadriven statistical techniques, e.g.,
nonlinear classification and regression machine
learning methods, play an increasingly important role
in applied data analysis and quantitative research. For
realworld we do not know a priori which methods will
work best. Furthermore, most of the available models
depend on so called hyper or control parameters, which
can drastically influence their performance. This leads
to a vast space of potential models, which cannot be
explored exhaustively. Modern optimization techniques,
often either evolutionary or modelbased, are employed
to speed up this process. A very similar problem occurs
in continuous and discrete optimization and, in
general, in many other areas where problem instances
are solved by algorithmic approaches: Many competing
techniques exist, some of them heavily parametrized.
Again, not much knowledge exists, how, given a certain
application, one makes the correct choice here. These
general problems are called algorithm selection and
algorithm configuration. Instead of relying on tedious,
manual trialanderror, one should rather employ
available computational power in a methodical fashion
to obtain an appropriate algorithmic choice, while
supporting this process with machinelearning
techniques to discover and exploit as much of the
search space structure as possible. In this cumulative
dissertation I summarize nine papers that deal with the
problem of model and algorithm selection in the areas
of machine learning and optimization. Issues in
benchmarking, resampling, efficient model tuning,
feature selection and automatic algorithm selection are
addressed and solved using modern techniques. I apply
these methods to tasks from engineering, music data
analysis and blackbox optimization. The dissertation
concludes by summarizing my published R packages for
such tasks and specifically discusses two packages for
parallelization on high performance computing clusters
and parallel statistical experiments.",

notes = "p14 'on the considered [SVM] benchmark problems even
our improved genetic programming approach leads to
disappointing results. Although goodperforming common
kernel functions can be recovered by the genetic
search'
In English",
 }
Genetic Programming entries for
Bernd Bischl
Citations