Statistical learning theory 2021

Материал из Wiki - Факультет компьютерных наук
Перейти к: навигация, поиск

General Information

Grading

Teachers: Bruno Bauwens and Nikita Lukianenko

Lectures: Saturday 14:40 - 16:00. The lectures are here in zoom.

Seminars: Tuesday 16:20 - 17:40. The seminars are here in google.meet.

Practical information on a telegram group. Join here.

The course is similar last year, except for the order of topics and part 3.

Colloquium

Saturday December 11

rules and list of questions (updated Nov 22, questions from lectures 1-11)

Homeworks

Email to brbauwens-at-gmail.com. Start the subject line with SLT-HW. Results

Deadline before the lecture, every other lecture.

25 Sept: see problem lists 1 and 2
09 Oct: see problem lists 3 and 4
29 Oct: see problem lists 5 and 6
13 Nov: see problem lists 7 and 8
30 Nov, 08:00 [extended]: see problem lists 9 and 10 Update 23 Nov: exercises 9.4 and 10.5b.
11 Dec: see problem lists 11 and 12

Course materials

Video Summary Slides Lecture notes Problem list Solutions
Part 1. Online learning
4 Sept Lecture: philosophy. Seminar: the online mistake bound model, the weighted majority, and perceptron algorithms movies sl01 ch00 ch01 01prob (9 Sept) 01sol
11 Sept The perceptron algorithm in the agnostic setting. Kernels. The standard optimal algorithm. sl02 ch02 ch03 02prob (23 Sept) 02sol
18 Sept (rec to do) Prediction with expert advice and the exponentially weighted majority algorithm. Recap probability theory. sl03 ch04 ch05 03prob(30 Sept) 03sol
Part 2. Risk bounds for binary classification
25 Sept Sample complexity in the realizable setting, simple examples and bounds using VC-dimension sl04 ch06 04prob 04sol
2 Oct Growth functions, VC-dimension and the characterization of sample comlexity with VC-dimensions sl05 ch07 ch08 05prob 05sol
9 Oct Risk decomposition and the fundamental theorem of statistical learning theory sl06 ch09 06prob 06sol
16 Oct Bounded differences inequality and Rademacher complexity sl07 ch10 ch11 07prob 07sol
30 Oct Simple regression, support vector machines, margin risk bounds, and neural nets sl08 ch12 ch13 08prob 08sol
6 Nov Kernels: risk bounds, RKHS, representer theorem, design sl09 ch14 09prob (Nov 23) 09sol
13 Nov AdaBoost and risk bounds sl10 Mohri et al, chapt 7 10prob (Nov 23) 10sol
Part 3. Other topics
20 Nov Clustering sl11 Mohri et al, ch7; lecture 11prob 11sol
27 Nov Dimensionality reduction and the Johnson-Lindenstrauss lemma
4 Dec No lecture
11 Dec Colloquium


The lectures in October and November are based on the book: Foundations of machine learning 2nd ed, Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalker, 2018. This book can be downloaded from http://gen.lib.rus.ec/ .

Office hours

Person Monday Tuesday Wednesday Thursday Friday
Bruno Bauwens, Zoom 12h30-14h30 14h-20h Room S834 Pokrovkaya 11
Nikita Lukianenko, Telegram 14h30-16h30 14h30-16h30 Room S831 Pokrovkaya 11

It is always good to send an email in advance. Questions and feedback are welcome.

I am traveling from Sept 12 -- Sept 30 and Oct 16 -- Oct 26. On Fridays I'm available till 16h30.