Information-Theoretic Learning (ITL)

Leiden University, Spring Semester 2018

General Information

Important: All students are requested to register for the course via blackboard (in addition to USIS).
Important: Bachelor students who want to investigate the possibility of letting (the EC of) this course count towards their master's diploma, are advised to contact the chairman of the Exam Committee (Ronald van Luijk, rvl@math.leidenuniv.nl) at their earliest convenience.
LecturerProf. Dr. Peter Grünwald, Leiden University, Mathematical Institute, and Centrum Wiskunde & Informatica (CWI), Amsterdam
Teaching assistantRianne de Heide, Leiden University, Mathematical Institute, and Centrum Wiskunde & Informatica (CWI), Amsterdam
Contact: send email to: r.de.heide at cwi.nl.

The URL of this webpage is www.cwi.nl/~pdg/teaching/inflearn. Visit this page regularly for changes, updates, etc.

This course is on an interesting but complicated subject. It is given at the master's or advanced bachelor's level. Although the only background knowledge required is elementary probability theory, the course does require serious work by the student. The course load is 6 ECTS. Click here (studiegids) for a general course description.

Many thanks are due to Steven de Rooij (Leiden University) who prepared a significant proportion of the exercises.

Lectures and Exercise Sessions

Lectures take place each Tuesday from 13.30--15.15 in room 405 of the Snellius Building, Niels Bohrweg 1, Leiden. The lectures are immediately followed by a mini-exercise session held by Rianne de Heide. The first lecture will take place February 6th, 2018. There will be no lectures on March 13, April 3 and April 17. The last official lecture is scheduled for May 22, and the final exam is provisionally scheduled for Monday May 28th (note: the official schedule says 'Tuesday May 28th', but that date does not exist!), 14.00-17.00, in room B02.

Homework Assignments

Weekly Homework: At every lecture on Tuesday except the first there is a homework assignment. The assignment will also be made available on this webpage. Homework is obligatory and must be turned in at or before the beginning of the next lecture, i.e. one week after the assignment was handed out. You can turn in your homework digitally via blackboard or (printed or handwritten) via teaching assistant Rianne de Heide's pigeon hole (postvakje) or by handing it over to me or Rianne at the beginning of the lecture. After the lecture, there is (approximately) 30 minutes homework session, during which the homework will be explained and discussed by Rianne. Turning in written complete homework in time is required, see below.

Credit

6 ECTS points.

Examination form

In order to pass the course, one must obtain a sufficient grade (6 or higher) on both of the following two:
  1. An open-book written examination (to be held Tuesday May 29th).
  2. Homework. Each student must hand in solutions to homework assignments at the beginning of the lecture after the homework was handed out. Discussing the problems in the group is encouraged, but every participant must write down her or his answers on her or his own. The final homework grade will be determined as an average of the weekly grades.
The final grade will be determined as the average of the two grades.

Literature

We will mainly use various chapters of the following source: P. Grünwald. The Minimum Description Length Principle, MIT Press, 2007. Some additional hand-outs will be made available free of charge as we go. For the second week, this is Luckiness and Regret in Minimum Description Length Inference, by Steven de Rooij and Peter Grünwald, Handbook of the Philosophy of Science, Volume 7: Philosophy of Statistics, 2011. This paper gives an overview of the part of this course that will be concerned with the relation between statistics, machine learning and data compression, as embodied in MDL learning.

Course Schedule

Lecture contents are subject to change at any time for any reason. A more precise schedule, with links to all exercises, will be determined as we go.
  1. February 6: introduction
  2. February 13: data compression without probability
  3. February 20: Codes and Probabilities (the most important lecture!)
  4. February 27: Preparatory Statistics.
  5. March 6:
  6. March 13th: No Lecture!
  7. March 20th: Universal Coding
  8. March 27th:
  9. April 3: No Lecture!
  10. April 10: Simple Refined MDL, Prequential Plugin Codes
  11. April 17: No Lecture!
  12. April 24: General Refined MDL, Prediction with MDL, Issues with Universal Codes/MDL
  13. May 1st: Excursion: Sequential Prediction with General Loss Functions
  14. May 8th: Excursion, Part II.
  15. May 15th: Maximum Entropy
  16. May 22nd: MaxEnt and MDL ; Overview/Wrap Up
  17. MONDAY May 2814:00-17:00: Open-Book Examination in Room B2 of the Snellius building.

    Peter Grünwald’s home page