Lecturer Varun Kanade
Hours Monday and Thursday 16h-18h
Location Lecture Theatre A

Note 1. Lecture notes will be posted for every lecture; however, they are not meant to be used as a substitute for actually reading the textbooks and other posted reading. Should you wish to read up ahead of lectures, you may follow the material posted on the Advanced Machine Learning course from Hilary Term 2017. However, please make sure to make use of the most updated material when revising.

Note 2. There will be parts of suggested reading material that you struggle with or may seem not directly related to what we covered in the lecture. I suggest you skip these sections and only return to them once you've understood the material covered in the lecture and want to increase your understanding further.

Note 3. I expect the total number of lecture hours to be between 20 and 24. Lectures are scheduled for 32 hours to make it convenient to adjust the timetable.

Lecture Schedule

Date Topic Handouts Reading

15/01/2018 Introduction & PAC learning framework [slides]

(KV) Chap 1
Valiant's paper

18/01/2018 Learning conjunctions,
Intractability of learning 3-term DNF,
Learning 3-CNF


(KV) Chap 1

25/01/2018 Consistent Learners; Occam's Razor [notes] (KV) Chap 2

29/01/2018 VC Dimension [notes] (KV) Chap 3

01/02/2018 Weak Learning and Boosting [notes] Adaboost survey
Adaboost article

05/02/2018 Cryptographic Hardness of Learning [notes] (KV) Chap. 6

08/02/2018 Learning using Membership and Equivalence Queries [notes]

(KV) Chap. 8
12/02/2018 Angluin's Algorithm,
Learning in the presence of noise

[notes] (KV) Chap. 8
15/02/2018 SQ Learning

[notes] (KV) Chap. 5
19/02/2018 SQ Lower Bounds,
Learning Real-valued Functions

[notes] (KV) Chap. 5
[Kearns' paper]

22/02/2018 Convex Optimization,
Generalised Linear Models,
Rademacher Complexity

[notes] Convex Opt. book (Chap. 3.1)