Optimal Data Distributions in Machine Learning
<p>In the first part of the thesis we explore three fundamental questions that arise naturally when we conceive a machine learning scenario where the training and test distributions can differ. Contrary to conventional wisdom, we show that in fact mismatched training and test distribution can...
Internet
https://thesis.library.caltech.edu/8888/73/CarlosGonzalez2015_thesis.pdfhttps://thesis.library.caltech.edu/8888/1/CarlosGonzalez2015_thesis-FrontMatter.pdf
https://thesis.library.caltech.edu/8888/7/CarlosGonzalez2015_thesis-TableOfContents.pdf
https://thesis.library.caltech.edu/8888/13/CarlosGonzalez2015_thesis-Chapter1.pdf
https://thesis.library.caltech.edu/8888/14/CarlosGonzalez2015_thesis-Chapter2.pdf
https://thesis.library.caltech.edu/8888/56/CarlosGonzalez2015_thesis-Chapter3.pdf
https://thesis.library.caltech.edu/8888/15/CarlosGonzalez2015_thesis-Chapter4.pdf
https://thesis.library.caltech.edu/8888/29/CarlosGonzalez2015_thesis-Chapter5.pdf
https://thesis.library.caltech.edu/8888/32/CarlosGonzalez2015_thesis-Chapter6.pdf
https://thesis.library.caltech.edu/8888/43/CarlosGonzalez2015_thesis-Chapter7.pdf
https://thesis.library.caltech.edu/8888/49/CarlosGonzalez2015_thesis-Conclusion.pdf
https://thesis.library.caltech.edu/8888/50/CarlosGonzalez2015_thesis-Appendix.pdf
https://thesis.library.caltech.edu/8888/51/CarlosGonzalez2015_thesis-Bibliography.pdf
González Palacios, Carlos Roberto (2015) Optimal Data Distributions in Machine Learning. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/Z9DR2SD5. https://resolver.caltech.edu/CaltechTHESIS:05262015-094933189 <https://resolver.caltech.edu/CaltechTHESIS:05262015-094933189>