RegML 2016
Regularization Methods for Machine Learning

Course at a Glance

The course will be held on June 27th - July 1st, 2016 at DIBRIS (University of Genoa, Italy)

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. Modern cameras recognize faces, and smart phones voice commands, cars can see and detect pedestrians and ATM machines automatically read checks. In most cases at the root of these success stories there are machine learning algorithms, that is softwares that are trained rather than programmed to solve a task. Among the variety of approaches to modern computational learning, we focus on regularization techniques, that are key to high- dimensional learning. Regularization 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 (aka manifold learning), sparsity and a variety of algorithms for supervised learning, feature selection, structured prediction, multitask learning and model selection. 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 laboratory sessions will give the opportunity to have hands on experience.

RegML is a 20 hours 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. In many respect the course is compressed version of the 9.520 course at MIT".

The course started in 2008 has seen an increasing national and international attendance over the years with a peak of over 90 participants in 2014.

NOTE: the course has no registration fee, but participants need to take care of their travel and accommodation needs -- see below for a list of hotels.

Notification of acceptance: May 1st.

Related courses:

Basic Info


Classes will take place at the Department of Informatics Bioengineering Robotics and Systems Engineering (DIBRIS) of the University of Genova in Via Dodecaneso 35, 16146 Genova. See here for directions and travelling information

(new!) Morning classes (theory) will be held in classroom 506. Laboratories will take place in rooms SW1,SW2 and 218. Directions to the classrooms will be provided at the DIBRIS entrance in Via Dodecaneso 35.


Genova is in the region of Liguria in the Italian Riviera (see here or here for some nice pics and a video).


Here you can find a list of hotels near the department (~ 20' walk) or in the city centre (~20' by bus).


Here is a list of places where you can go for lunch. And here is a link to the online map.


Lorenzo Rosasco

Universita' di Genova
(also Istituto Italiano di Tecnologia and Massachusetts Institute of Technology)

lorenzo (dot) rosasco (at) unige (dot) it


Invited Speakers

Prof. Gadi Geiger

Massachusetts Institute of Technology

Prof. Federico Girosi

Western Sydney University
Capital Markets CRC Limited

Prof. Massimiliano Pontil

University College London
Istituto Italiano di Tecnologia

Prof. Thomas Vetter

University of Basel

Prof. Alessandro Verri

Università degli Studi di Genova


1Mon 6/279:30 - 11:00Introduction to Statistical Machine LearningLect_1
2Mon 6/2711:30 - 13:00Tikhonov Regularization and KernelsLect_2
3Mon 6/2714:00 - 16:00Laboratory 1: Binary classification and model selection Lab 1
4Tue 6/289:30 - 11:00Early Stopping and Spectral RegularizationLect_3
5Tue 6/2811:30 - 13:00Regularization for Multi-task LearningLect_4
6Tue 6/2814:00 - 16:00Laboratory 2: Spectral filters and multi-class classificationLab 2
-Wed 6/299:30 - 10:00Workshop: Federico Girosi - Health Analytics and Machine Learning
-Wed 6/2910:00 - 10:30Workshop: Massimiliano Pontil - A Class of Regularizers based on Optimal Interpolation
-Wed 6/2910:30 - 11:00Workshop: Gadi Geiger - Visual and Auditory Aspects of Perception in Developmental Dyslexia
-Wed 6/2911:00 - 11:30Coffee Break
-Wed 6/2911:30 - 12:00Workshop: Alessandro Verri - Extracting Biomedical Knowledge through Regularized Learning Techniques
-Wed 6/2912:00 - 12:30Workshop: Thomas Vetter - Learning the Appearance of Faces: Probabilistic Morphable Models
-Wed 6/29AfternoonFree
7Thu 6/309:30 - 11:00Sparsity Based RegularizationLect_5
8Thu 6/3011:30 - 13:00Structured SparsityLect_6
9Thu 6/3014:00 - 16:00Laboratory 3: Sparsity-based learningLab 3
10Fri 7/19:30 - 11:00Data Representation: Dictionary LearningLect_7
11Fri 7/1 11:30 - 13:00Data Representation: Deep LearningLect_8

Subscriptions are now closed. Results will be emailed soon.
For any inquiries, please write to


Alessandro Rudi

Università di Genova
Laboratory for Computational and Statistical Learning

ale_rudi (at) mit (dot) edu

Raffaello Camoriano

iCub Facility (also Laboratory for Computational and Statistical Learning)
Istituto Italiano di Tecnologia
DIBRIS, Università degli Studi di Genova

raffaello (dot) camoriano (at) iit (dot) it

Silvia Villa

Laboratory for Computational and Statistical Learning
Istituto Italiano di Tecnologia

silvia (dot) villa (at) iit (dot) it