E2 236, Spring 2021

Foundations of Machine Learning

Lectures

• 23 Feb 2021: Lecture-01 Introduction
• 25 Feb 2021: Lecture-02 Review of Linear algebra and convex optimization
• 02 Mar 2021: Lecture-03 Support Vector Machines – separable case
• 04 Mar 2021: Lecture-04 Support Vector Machines – non-separable case
• 09 Mar 2021: Lecture-05 Reproducing Kernel Hilbert Space (RKHS)
• 11 Mar 2021: Lecture-06 Positive Definite Symmetric (PDS) Kernels
• 16 Mar 2021: Lecture-07 Probably Approximately Correct (PAC) Learning
• 18 Mar 2021: Lecture-08 Rademacher Complexity
• 23 Mar 2021: Lecture-09 VC Dimensions
• 25 Mar 2021: Lecture-10 Margin Theory
• 30 Mar 2021: Lecture-11 Multiclass Classification-01
• 01 Apr 2021: Lecture-12 Multiclass Classification-02
• 06 Apr 2021: Lecture-13 Multiclass Classification-03
• 08 Apr 2021: Lecture-14 Point Estimation

Homework

• 06 Mar 2021: Homework-01
• 13 Mar 2021: Homework-02
• 27 Mar 2021: Homework-03
• 04 Apr 2021: Homework-04

Programming Assignments

• 12 Mar 2021: Programming Assignment 1 Submission date: 22 Mar 2021
• 23 Mar 2021: Programming Assignment 2 Assignment_2_yourname.xlsx Submission date: 01 Apr 2021

Tests

• 19 Mar 2021: Quiz-01
• 26 Mar 2021: Quiz-02
• 09 Apr 2021: Quiz-03
• 16 Apr 2021: Mid-term

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
• Multiclass classification
• Parameter estimation and nonparametric regression
• Convex optimization, Stochastic gradient descent
• Neural Networks, Deep learning
• Reinforcement learning and deep reinforcement learning
• Online learning
• Dim reduction, feature representation/extraction, clustering.

Course Description

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

Teams/GitHub Information

Teams

We will use Microsoft Teams for all the course related communication.
Please do not send any email regarding the course.
You can signup for the course team Foundations-Machine-Learning-2021 using the following code woald5z.
To be on the course team, you have to be formally registered for the course.
If you are registered for the course and not on the course team Foundations-Machine-Learning-2021, please send me a direct message on Teams.

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 03:30-05:00pm.
Tutorial/Quiz: Fri 07:50am, EC 1.08.

Teaching Assistant

Himanshu Kumar
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