Statistical learning theory 2020 — различия между версиями

Материал из Wiki - Факультет компьютерных наук
Перейти к: навигация, поиск
Строка 16: Строка 16:
 
- Sat 17 Oct: see problem lists 3 and 4<br>
 
- Sat 17 Oct: see problem lists 3 and 4<br>
 
- Sat 31 Oct: see problem list 5<br>
 
- Sat 31 Oct: see problem list 5<br>
- Sat 14 Nov: see problem lists 6 and 7 <span style="color:red">Update 11.11</span><br>
+
- Sat 14 Nov: see problem lists 6 and 7 <br>
- Sat 28 Nov: see problem lists 8 and 9<br>
+
- Sat 28 Nov: see problem lists 8 and 9 <span style="color:red">Update 11.11</span><br>
 
- Sat 12 Dec: see problem lists 10 and 11
 
- Sat 12 Dec: see problem lists 10 and 11
  
Строка 97: Строка 97:
 
|| [https://www.dropbox.com/s/rtlsy6ssm2yj2p0/09slides.pdf?dl=0 slides9.pdf]
 
|| [https://www.dropbox.com/s/rtlsy6ssm2yj2p0/09slides.pdf?dl=0 slides9.pdf]
 
||  
 
||  
|| [https://www.dropbox.com/s/k0ynyl5x874e0gq/09sem.pdf?dl=0 Problem list 9]
+
|| [https://www.dropbox.com/s/k0ynyl5x874e0gq/09sem.pdf?dl=0 Problem list 9] <span style="color:red">Update 26.11, HW 9.5</span>
 
|| [https://www.dropbox.com/s/k2zpqnoiwe19osu/09sol.pdf?dl=0 Solutions 9]
 
|| [https://www.dropbox.com/s/k2zpqnoiwe19osu/09sol.pdf?dl=0 Solutions 9]
 
|-
 
|-

Версия 20:31, 26 ноября 2020

General Information

Teachers: Bruno Bauwens and Vladimir Podolskii

Lectures: Saturday 9h30 - 10h50, zoom https://zoom.us/j/96210489901

Seminars
- Group 1: Saturday 11h10 - 12h30, Bruno Bauwens and Vladimir Podolskii zoom https://zoom.us/j/94186131884,
- Group 2: Tuesday 18h, Nikita Lukyanenko, see ruz.hse.ru

Practical information on telegram group

Homeworks: deadlines every 2 weeks, before the lecture.
- Sat 3 Oct: see problem lists 1 and 2
- Sat 17 Oct: see problem lists 3 and 4
- Sat 31 Oct: see problem list 5
- Sat 14 Nov: see problem lists 6 and 7
- Sat 28 Nov: see problem lists 8 and 9 Update 11.11
- Sat 12 Dec: see problem lists 10 and 11

Results.

Email homeworks to Brbauwens <at> gmail.com. Start the subject line with SLT-HW. You may submit handwritten solutions.


Colloquium

Saturday 12 Dec and Tuesday 15 Dec, online

What: basic definitions, proofs of 2-3 main results in each lecture. Rules and questions.

Course materials

Date Summary Lecture notes Slides Video Problem list Solutions
12 Sept Introduction and sample complexity in the realizable setting lecture1.pdf slides1.pdf Problem list 1 Update 26.09, prob 1.7 Solutions 1
19 Sept VC-dimension and sample complexity lecture2.pdf slides2.pdf Chapt 2,3 Problem list 2 Solutions 2
26 Sept Risk bounds and the fundamental theorem of statistical learning theory lecture3.pdf slides3.pdf Problem list 3 Solutions 3
03 Oct Rademacher complexity lecture4.pdf slides4.pdf Problem list 4 Update 23.10, prob 4.1d Solutions 4
10 Oct Support vector machines and risk bounds Chapt 5, Mohri et al, see below slides5.pdf Problem list 5 Update 29.10, typo 5.8 Solutions 5
17 Oct Support vector machines and recap Chapt 5, Mohri et al. slides6.pdf Problem list 6 Update 10.11 Solutions 6
31 Oct Kernels lecture7.pdf slides7.pdf Problem list 7 Update 11.11, prob 7.6 Solutions 7
07 Nov Adaboost Chapt 6, Mohri et al slides8.pdf Problem list 8 Solutions 8
14 Nov Online learning 1, Littlestone dimension, weighted majority algorithm Chapt 7, Mohri et al, and Животовский slides9.pdf Problem list 9 Update 26.11, HW 9.5 Solutions 9
21 Nov Online learning 2, Exponential weighted average algorithm, preceptron Chapt 7, Mohri et al slides9.pdf Problem list 10
28 Nov Online to batch conversion, unsupervised learning
5 Dec Recap of requested topics, Q&A


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/ .

For online learning, we also study a few topics from lecture notes by Н. К. Животовский

Office hours

Person Monday Tuesday Wednesday Thursday Friday
Bruno Bauwens 14h-18h 16h15-20h Room S834 Pokrovkaya 11

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