E2 336, Fall 2019 | Parimal Parag

Foundations of Machine Learning

Lectures

06 Aug 2019: Lecture-01 Introduction
08 Aug 2019: Lecture-02 Support Vector Machines – separable case
13 Aug 2019: Lecture-03 Support Vector Machines – non-separable case
14 Aug 2019: Lecture-04 Reproducing Kernel Hilbert Space (RKHS)
20 Aug 2019: Lecture-05 Positive Definite Symmetric (PDS) Kernels
22 Aug 2019: Lecture-06 Probably Approximately Correct (PAC) Learning
27 Aug 2019: Lecture-07 Rademacher Complexity
29 Aug 2019: Lecture-08 VC Dimensions
03 Sep 2019: Lecture-09 Margin Theory
05 Sep 2019: Lecture-10
10 Sep 2019: Lecture-11
12 Sep 2019: Lecture-12 Multiclass Classification and Generative Models
17 Sep 2019: Lecture-13 PAC Bayes and Parameter Estimation
19 Sep 2019: Lecture-14 Gaussian Mixtures and EM agorithm
24 Sep 2019: Lecture-15 Non-parametric Regression

Homework

15 Aug 2019: Homework-01
29 Aug 2019: Homework-02
07 Sep 2019: Homework-03
23 Sep 2019: Homework-04
11 Oct 2019: Homework-05
25 OCt 2019: Homework-06
11 Nov 2019: Homework-07
26 Nov 2019: Homework-08

Programming Assignments

24 Aug 2019: Programming Assignment 1. Submission date: 10 Sep 2019
07 Sep 2019: Programming Assignment 2. Assignment_2_yourname.xlsx. Submission date: 25 Sep 2019
26 Sep 2019: Programming Assignment 3. Submission date: 14 Oct 2019
15 Oct 2019: Programming Assignment 4. Submission date: 30 Oct 2019
04 Nov 2019: Programming Assignment 5. PA_5.xlsx. PA_5.py. Submission date: 20 Nov 2019
16 Nov 2019: Programming Assignment 6. PA_6.py. Submission date: 30 Nov 2019

Tests

24 Aug 2019: Quiz-01
09 Sep 2019: Quiz-02
23 Sep 2019: Quiz-03
05 Oct 2019: Mid-term
21 Oct 2019: Quiz-04
04 Nov 2019: Quiz-05
25 Nov 2019: Quiz-06
06 Dec 2019: Final

Grading Policy

Quiz : 20
Assignments : 30
Mid Term : 20
Final : 30

Course Syllabus

Support Vector Machines, Kernel methods
PAC learning framework, learning via uniform convergence
Bias complexity trade-off, Rademacher complexity, VC-dimension
Online learning, clustering, dimensionality reduction, reinforcement learning
Linear predictors, regression, boosting, model selection, convex learning, regularization, algorithmic stability
Multi-class classification, ranking, decision trees, nearest neighbors, neural networks

Course Description

This course provides performance guarantees on various classes of machine learning algorithms.

Slack/GitHub Information

Slack

Students can signup for course slack using their iisc.ac.in email at Slack signup.
Add yourself to the public channel #ml-2019.
If you don’t have an IISc email, please talk to the instructor.

GitHub

Students can signup for GitHub here.
All the students in the class have read access to Machine-Learning public repository on GitHub.
For the write access to this GitHub repository, please send me your github userid on the course slack channel.
GitHub would be used for scribing lecture notes and submitting programming assignments.
Please follow the guidelines in the sample lecture.
The source file for the sample lecture is in the repository.
It is recommended you save it with another name in your local repository for creating a new lecture.
A good book for Git is here and a simple tutorial here.

Instructors

Vinod Sharma
Office: EC 2.07
Hours: By appointment.

Parimal Parag
Office: EC 2.17
Hours: By appointment.

Time and Location

Classroom: Auditorium 1, MP 20, ECE MP Building
Hours: Tu-Th 03:45-05:15pm.
Tutorial/Quiz: Mon 06:00pm, EC 1.08.

Teaching Assistant

Sarvendranath Rimalapudi
Office: SPW 202
Hours: By appointment.

Textbooks

Foundations of machine learning, Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar
Understanding machine learning, Shai Shalev-Shwartz and Shai Ben-David