Statistical learning theory 2021 — различия между версиями
Материал из Wiki - Факультет компьютерных наук
Bbauwens (обсуждение | вклад) |
Bbauwens (обсуждение | вклад) |
||
| (не показано 36 промежуточных версии 2 участников) | |||
| Строка 6: | Строка 6: | ||
Teachers: [https://www.hse.ru/en/org/persons/160550073 Bruno Bauwens] and [https://www.hse.ru/en/org/persons/225553845 Nikita Lukianenko] | Teachers: [https://www.hse.ru/en/org/persons/160550073 Bruno Bauwens] and [https://www.hse.ru/en/org/persons/225553845 Nikita Lukianenko] | ||
| − | Lectures: Saturday 14:40 - 16:00. The lectures are | + | Lectures: Saturday 14:40 - 16:00. The lectures are in zoom. |
Seminars: Tuesday 16:20 - 17:40. The seminars are [https://meet.google.com/ber-yzns-hxz here] in google.meet. | Seminars: Tuesday 16:20 - 17:40. The seminars are [https://meet.google.com/ber-yzns-hxz here] in google.meet. | ||
| − | + | Practical information on a telegram group. | |
| − | + | ||
| − | Practical information on a telegram group. | + | |
The course is similar [http://wiki.cs.hse.ru/Statistical_learning_theory_2020 last year], except for the order of topics and part 3. | The course is similar [http://wiki.cs.hse.ru/Statistical_learning_theory_2020 last year], except for the order of topics and part 3. | ||
| + | |||
| + | == Problems exam == | ||
| + | |||
| + | Dec 22, 12:00 -- 15:30 | ||
| + | |||
| + | During the exam<br> | ||
| + | -- You may consult notes, books and search on the internet <br> | ||
| + | -- You may not interact with other humans (e.g. by phone, forums, etc) | ||
== Colloquium == | == Colloquium == | ||
| Строка 20: | Строка 26: | ||
Saturday December 11 | Saturday December 11 | ||
| − | [https://www.dropbox.com/s/u8hyo1omvaoujle/colloqQuest.pdf?dl=0 rules and list of questions] ( | + | [https://www.dropbox.com/s/u8hyo1omvaoujle/colloqQuest.pdf?dl=0 rules and list of questions] (version Dec 10) |
== Homeworks == | == Homeworks == | ||
| − | Email to brbauwens-at-gmail.com. Start the subject line with SLT-HW. [https://www.dropbox.com/s/ | + | Email to brbauwens-at-gmail.com. Start the subject line with SLT-HW. [https://www.dropbox.com/s/prsmzhtr5p5uome/scores.pdf?dl=0 Results] |
Deadline before the lecture, every other lecture. | Deadline before the lecture, every other lecture. | ||
| Строка 30: | Строка 36: | ||
25 Sept: see problem lists 1 and 2 <br> | 25 Sept: see problem lists 1 and 2 <br> | ||
09 Oct: see problem lists 3 and 4 <br> | 09 Oct: see problem lists 3 and 4 <br> | ||
| − | 29 Oct: see problem lists 5 and 6 <br | + | 29 Oct: see problem lists 5 and 6 <br> |
13 Nov: see problem lists 7 and 8 <br> | 13 Nov: see problem lists 7 and 8 <br> | ||
| − | + | 30 Nov, 08:00 [extended]: see problem lists 9 and 10 | |
| − | + | ||
== Course materials == | == Course materials == | ||
| Строка 107: | Строка 112: | ||
|| [https://www.dropbox.com/s/nhqtbekclekf6k7/09slides.pdf?dl=0 sl09] | || [https://www.dropbox.com/s/nhqtbekclekf6k7/09slides.pdf?dl=0 sl09] | ||
|| [https://www.dropbox.com/s/bpb9ijn2p7k19j3/14book_kernels.pdf?dl=0 ch14] | || [https://www.dropbox.com/s/bpb9ijn2p7k19j3/14book_kernels.pdf?dl=0 ch14] | ||
| − | || [https://www.dropbox.com/s/d2dmh017lw207ns/09sem.pdf?dl=0 09prob] | + | || [https://www.dropbox.com/s/d2dmh017lw207ns/09sem.pdf?dl=0 09prob] (Nov 23) |
|| [https://www.dropbox.com/s/2wq9mxrqchsqujr/09sol.pdf?dl=0 09sol] | || [https://www.dropbox.com/s/2wq9mxrqchsqujr/09sol.pdf?dl=0 09sol] | ||
|- | |- | ||
| Строка 114: | Строка 119: | ||
|| [https://www.dropbox.com/s/umum3kd9439dt42/10slides.pdf?dl=0 sl10] | || [https://www.dropbox.com/s/umum3kd9439dt42/10slides.pdf?dl=0 sl10] | ||
|| Mohri et al, chapt 7 | || Mohri et al, chapt 7 | ||
| − | || [https://www.dropbox.com/s/j8s197e0mjv9qla/10sem.pdf?dl=0 10prob] | + | || [https://www.dropbox.com/s/j8s197e0mjv9qla/10sem.pdf?dl=0 10prob] (Nov 23) |
| − | || | + | || [https://www.dropbox.com/s/7lw1u8750k7s8qt/10sol.pdf?dl=0 10sol] |
|- | |- | ||
| | | | ||
| Строка 123: | Строка 128: | ||
|| Clustering | || Clustering | ||
|| [https://www.dropbox.com/s/5a9flvg95iihz7m/11slides.pdf?dl=0 sl11] | || [https://www.dropbox.com/s/5a9flvg95iihz7m/11slides.pdf?dl=0 sl11] | ||
| − | || Mohri et al, | + | || Mohri et al, ch7; [https://people.csail.mit.edu/dsontag/courses/ml12/slides/lecture14.pdf lecture] |
| − | || | + | || <!-- [https://www.dropbox.com/s/a9459keof3omav1/11sem.pdf?dl=0 11prob] --> |
| − | || | + | || <!-- [https://www.dropbox.com/s/kredac52pbn7qvk/11sol.pdf?dl=0 11sol] --> |
|- | |- | ||
| − | | 27 Nov | + | | [https://youtu.be/FN6l4Ceq5lE 27 Nov] |
|| Dimensionality reduction and the Johnson-Lindenstrauss lemma | || Dimensionality reduction and the Johnson-Lindenstrauss lemma | ||
| − | || | + | || [https://www.dropbox.com/s/wbgwwk7a9mjo1bv/12slides.pdf?dl=0 sl12] |
| − | || | + | || Mohri et al, ch15; [https://ramanlab.wustl.edu/Lectures/Lecture12_LDA_CCA.pdf lecture] |
| − | || | + | || [https://www.dropbox.com/s/c5anx2htaw9rslr/12sem.pdf?dl=0 12prob] |
|| | || | ||
|- | |- | ||
| Строка 147: | Строка 152: | ||
|| | || | ||
|| | || | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
|} | |} | ||
| Строка 254: | Строка 174: | ||
It is always good to send an email in advance. Questions and feedback are welcome. | It is always good to send an email in advance. Questions and feedback are welcome. | ||
| − | |||
| − | |||
<!-- | <!-- | ||
Текущая версия на 14:35, 16 декабря 2022
Содержание
General Information
Teachers: Bruno Bauwens and Nikita Lukianenko
Lectures: Saturday 14:40 - 16:00. The lectures are in zoom.
Seminars: Tuesday 16:20 - 17:40. The seminars are here in google.meet.
Practical information on a telegram group.
The course is similar last year, except for the order of topics and part 3.
Problems exam
Dec 22, 12:00 -- 15:30
During the exam
-- You may consult notes, books and search on the internet
-- You may not interact with other humans (e.g. by phone, forums, etc)
Colloquium
Saturday December 11
rules and list of questions (version Dec 10)
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
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 | ||
| 27 Nov | Dimensionality reduction and the Johnson-Lindenstrauss lemma | sl12 | Mohri et al, ch15; lecture | 12prob | |
| 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.
