This thesis discusses topics in High Dimensional Probability and shows an application of these to Machine Learning. In particular, we describe the sub-Gaussian distribution, random processes, and the use of covering numbers in the Chaining technique used to prove Dudley's inequality. These theoretical tools were then used for application to Statistical Learning Theory.
This thesis discusses topics in High Dimensional Probability and shows an application of these to Machine Learning. In particular, we describe the sub-Gaussian distribution, random processes, and the use of covering numbers in the Chaining technique used to prove Dudley's inequality. These theoretical tools were then used for application to Statistical Learning Theory.
Chaining and covering numbers with applications to Statistical Learning Theory
MAGNINO, LORENZO
2021/2022
Abstract
This thesis discusses topics in High Dimensional Probability and shows an application of these to Machine Learning. In particular, we describe the sub-Gaussian distribution, random processes, and the use of covering numbers in the Chaining technique used to prove Dudley's inequality. These theoretical tools were then used for application to Statistical Learning Theory.File | Dimensione | Formato | |
---|---|---|---|
Thesis__Chaining_and_Covering_Numbers_and_applications_to_Statistical_Learning_Theory-A.pdf
accesso riservato
Dimensione
782.21 kB
Formato
Adobe PDF
|
782.21 kB | Adobe PDF |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/32714