School on Regularization Methods for Machine Learning

Understanding how intelligence works and how it can be emulated in machines is an age old dream and arguably one of the biggest challenges in modern science. Learning, with its principles and computational implementations, is at the very core of this endeavor. Recently, for the first time, we have been able to develop artificial intelligence systems able to solve complex tasks considered out of reach for decades. In most cases at the root of the success stories there are machine learning algorithms, that is software that is trained rather than programmed to solve a task. RegML is a 22-hour advanced machine learning course including theory classes and practical laboratory sessions. The course covers foundations as well as recent advances in machine learning with emphasis on high dimensional data and a core set techniques, namely regularization methods. These methods allow to treat in a unified way a huge class of diverse approaches, while providing tools to design new ones. Starting from classical notions of smoothness, shrinkage and margin, the course will cover state-of-the-art techniques based on the concepts of geometry, sparsity and a variety of algorithms for supervised learning, feature selection, and multitask learning. Practical applications for high dimensional problems, in particular in computational vision, will be discussed. The classes will focus on algorithmic and methodological aspects, while trying to give an idea of the underlying theoretical underpinnings. Practical sessions will give the opportunity to have hands on experience. In many respect the course is compressed version of the 9.520 course at MIT. The school started in Genova, Italy, in 2008 has seen an increasing national and international attendance over the years with a peak of over 90 participants in 2014. This year (2-6 May 2017) RegML will be hosted and organized by Simula in Oslo. The course will be fully complementary to the courses taught at UiO.