Regularization Methods for Machine Learning

Regularization Methods for Machine Learning
Speaker:  Prof. Sergei Perevrzyev - RICAM Linz, Austria
  Monday, April 23, 2018 at 11:30 AM first lecture. Room G
TTitle: "Regularization Methods for Machine Learning"

Lecturer: Prof. S. Pereverzyev (RICAM - Linz, Austria)

Program and timetable :
Lecture 1 (23.04.2018) aula G 11.30-13.30 "Mathematical Aspects of Data Science. Supervised learning as an ill-posed inverse problem."
Lecture 2 (24.04.2018) aula M 11.30-13.30 "Basics of the Regularization theory. Single-parameter regularization schemes"
Lecture 3 (26.04.2018) aula M 8.30-10.30 "Kernel Ridge Regression and beyond. Learning rates for regression and ranking settings".
Lecture 4 (27.04.2018) aula M 13.30-15.30 "Data-driven choice of regularization parameters. Balancing principle & Co".
Lecture 5 (30.04.2018) aula G 9.30-11.30 "Aggregation of regularized learners. Linear functional strategy"
Lecture 6 (02.05.2018) aula Tessari 14.30-16.30 "Multiple kernel learning. Illustration by an application to diabetes technology"
Lecture 7 (03.05.2018) aula M 14.30-17.30 "Multiple penalty regularization and semi-supervised learning"

 
The course will mainly follow the Chapters 2 and 4 of the book "Regularization Theory for Ill-posed Problems: Selected Topics"
https://www.degruyter.com/view/product/182792
The dates in brackets are preliminary, final timetable will be announcd soon

contact persons: Giacomo Albi, Giandomenico Orlandi

Programme Director
Giandomenico Orlandi

External reference
Publication date
February 23, 2018

Studying

Share