This is course was offered in the online mode.
The course is divided into 3 modules. (In an in-person semester more modules will be covered.)Module 1
Foundations of theoretical machine learning: statistical learning, PAC and agnostic PAC learning, VC dimension, Fundamental Theorem of Statistical Machine learning.
Module 2
Online machine learning: mistake bounds, Littlestone's dimension, regret bounds, weighted majority algorithms (WMA), online convex optimisation and its applications to prediction theory and game theory.
Module 3
Advanced topics: Theoretical inquiries about Neural Networks (NN) such as understanding depth bounds, VC dimension of NN. Theory of reinforcement learning. Algorithms with predictions.