Statistical learning theory 2021 — различия между версиями
Материал из Wiki - Факультет компьютерных наук
Bbauwens (обсуждение | вклад) |
Bbauwens (обсуждение | вклад) |
||
| Строка 26: | Строка 26: | ||
|| Introduction, the online mistake bound model, the weighted majority and perceptron algorithms | || Introduction, the online mistake bound model, the weighted majority and perceptron algorithms | ||
|| | || | ||
| + | || | ||
|| | || | ||
|- | |- | ||
| Строка 31: | Строка 32: | ||
|| The standard optimal algorithm, prediction with expert advice, exponentially weighted algorithm | || The standard optimal algorithm, prediction with expert advice, exponentially weighted algorithm | ||
|| | || | ||
| + | || | ||
|| | || | ||
|- | |- | ||
| 21 Sept | | 21 Sept | ||
|| Better mistake bounds using VC-dimensions. Recap probability theory. Leave on out risk for SVM. | || Better mistake bounds using VC-dimensions. Recap probability theory. Leave on out risk for SVM. | ||
| + | || | ||
|| | || | ||
|| | || | ||
| Строка 43: | Строка 46: | ||
| 28 Sept | | 28 Sept | ||
|| Sample complexity in the realizable setting, simple example and bounds using VC-dimension | || Sample complexity in the realizable setting, simple example and bounds using VC-dimension | ||
| + | || | ||
|| | || | ||
|| | || | ||
| Строка 48: | Строка 52: | ||
| 5 Oct | | 5 Oct | ||
|| Risk decomposition and the fundamental theorem of statistical learning theory | || Risk decomposition and the fundamental theorem of statistical learning theory | ||
| + | || | ||
|| | || | ||
|| | || | ||
| Строка 53: | Строка 58: | ||
| 12 Oct | | 12 Oct | ||
|| Rademacher complexity | || Rademacher complexity | ||
| + | || | ||
|| | || | ||
|| | || | ||
| Строка 59: | Строка 65: | ||
|| Support vector machines and margin risk bounds | || Support vector machines and margin risk bounds | ||
|| | || | ||
| + | || | ||
|| | || | ||
|- | |- | ||
| 2 Nov | | 2 Nov | ||
|| Kernels: risk bounds, design, and representer theorem | || Kernels: risk bounds, design, and representer theorem | ||
| + | || | ||
|| | || | ||
|| | || | ||
| Строка 68: | Строка 76: | ||
| 9 Nov | | 9 Nov | ||
|| AdaBoost and risk bounds | || AdaBoost and risk bounds | ||
| + | || | ||
|| | || | ||
|| | || | ||
| Строка 77: | Строка 86: | ||
|| Clustering | || Clustering | ||
|| | || | ||
| + | || | ||
|| | || | ||
|- | |- | ||
| 23 Nov | | 23 Nov | ||
|| Dimensionality reduction and the Johnson-Lindenstrauss lemma | || Dimensionality reduction and the Johnson-Lindenstrauss lemma | ||
| + | || | ||
|| | || | ||
|| | || | ||
| Строка 86: | Строка 97: | ||
| 30 Nov | | 30 Nov | ||
|| Active learning | || Active learning | ||
| + | || | ||
|| | || | ||
|| | || | ||
|- 7 or 14 Dec | |- 7 or 14 Dec | ||
|| Colloquium | || Colloquium | ||
| + | || | ||
|| | || | ||
|| | || | ||
Версия 12:39, 2 сентября 2021
General Information
Teachers: Bruno Bauwens and Nikita Lukianenko
Lectures: Tuesdays 9h30 - 10h50, zoom
Seminars: Tuesday 11h10 - 12h30
Practical information on telegram group
Course materials
| Date | Summary | Lecture notes | Problem list | Solutions |
|---|---|---|---|---|
| Part 1. Online learning | ||||
| 7 Sept | Introduction, the online mistake bound model, the weighted majority and perceptron algorithms | |||
| 14 Sept | The standard optimal algorithm, prediction with expert advice, exponentially weighted algorithm | |||
| 21 Sept | Better mistake bounds using VC-dimensions. Recap probability theory. Leave on out risk for SVM. | |||
| Part 2. Supervised classification | ||||
| 28 Sept | Sample complexity in the realizable setting, simple example and bounds using VC-dimension | |||
| 5 Oct | Risk decomposition and the fundamental theorem of statistical learning theory | |||
| 12 Oct | Rademacher complexity | |||
| 26 Oct | Support vector machines and margin risk bounds | |||
| 2 Nov | Kernels: risk bounds, design, and representer theorem | |||
| 9 Nov | AdaBoost and risk bounds | |||
| Part 3. Other topics | ||||
| 16 Nov | Clustering | |||
| 23 Nov | Dimensionality reduction and the Johnson-Lindenstrauss lemma | |||
| 30 Nov | Active learning | |||
| 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 (email in advance) | 12h30-14h30 | 14h-20h | Room S834 Pokrovkaya 11 |
It is always good to send an email in advance. Questions and feedback are welcome.
