Foundations of Data Science

COM-406

Media

COM-406 Foundations of data science

26.2, Lecture 26.2 - Generalization Error

22.12.2021, 19:33

26.1, Lecture 26.1 - Generalization Error

22.12.2021, 12:46

25.1, Lecture 25.1 - Exploration Bias

17.12.2021, 10:32

25.2, Lecture 25.2 - Exploration Bias

17.12.2021, 10:19

24.2, Lecture 24.2 - Compression

16.12.2021, 18:07

24.1, Lecture 24.1 - Compression

16.12.2021, 17:28

23.2, Lecture 23.2 - Johnson-Lindenstrauss

10.12.2021, 13:29

23.1, Lecture 23.1 - PCA

10.12.2021, 13:19

22.3, Lecture 22.3 - Compression

08.12.2021, 16:58

22.2, Lecture 22.2 - Compression

08.12.2021, 16:50

22.1, Lecture 22.1 - Compression

08.12.2021, 16:46

21.3, Lecture 21.3 - Compression

03.12.2021, 15:00

21.2, Lecture 21.2 - Compression

03.12.2021, 14:33

21.1, Lecture 21.1 - Exponential Family

03.12.2021, 14:22

20.2, Lecture 20.2 - Exponential Family

01.12.2021, 12:21

20.1, Lecture 20.1 - Exponential Family

01.12.2021, 12:17

19.2, Lecture 19.2 - Exponential Family

27.11.2021, 22:09

19.1, Lecture 19.1 - Exponential Family

26.11.2021, 19:13

18.2, Lecture 18.2 - Detection & Estimation

24.11.2021, 22:57

18.1, Lecture 18.1 - Detection-Estimation

24.11.2021, 22:37

17.2, Lecture 17.2 - Detection & Estimation

21.11.2021, 18:08

17.1, Lecture 17.1 - Detection & Estimation

21.11.2021, 13:30

16.2, Lecture 16.2 - Detection & Estimation

13.11.2021, 20:01

16.1, Lecture 16.1 - Detection & Estimation

13.11.2021, 19:05

15, Lecture 15 - Property Testing

10.11.2021, 13:27

14.2, Lecture 14.2 - Distribution Estimation

08.11.2021, 10:24

14.1, Lecture 14.1 - Distribution Estimation

08.11.2021, 09:42

13.2, Lecture 13.2 - Distribution Estimation

03.11.2021, 18:56

13.1, Lecture 13.1 - Distribution Estimation

03.11.2021, 18:41

12.2, Lecture 12.2 - Distribution Estimation

30.10.2021, 12:05

12.1, Lecture 12.1 - Multi-arm Bandits

30.10.2021, 11:43

11.2, Lecture 11.2 - Multi-arm Bandits

27.10.2021, 14:47

11.1, Lecture 11.1 - Multi-arm Bandits

27.10.2021, 13:36

10.1, Lecture 10.1 - Multi-arm Bandits

25.10.2021, 13:18

10.2, Lecture 10.2 - Multi-arm Bandits

22.10.2021, 10:17

9.2, Lecture 9.2 - Multi-arm Bandits

21.10.2021, 14:16

9.1, Lecture 9.1 - Multi-arm Bandits

21.10.2021, 13:47

8.1, Lecture 8.1 - signal representations

12.10.2020, 12:23

8.2, Lecture 8.2 - Signal Representations

15.10.2021, 10:07

7.2, Lecture 7.2 - signal representations

09.10.2020, 11:19

7.1, Lecture 7.1 - Signal Representations

09.10.2020, 11:19

6.2, Lecture 6.2 - signal representations

05.10.2020, 11:49

6.1, Lecture 6.1 - signal representations

05.10.2020, 11:59

5.2, Lecture 5.2 - Signal Representations

07.10.2021, 09:48

5.1, Lecture 5.1 - Signal Representations

07.10.2021, 09:24

4.2, Lecture 4.2 - Linear Algebra Review

01.10.2021, 10:36

4.1, Lecture 4.1 - Information Measures

01.10.2021, 10:20

3.2, Lecture 3.2 information measures

25.09.2020, 10:46

3.1, Lecture 3.1 - information measures

25.09.2020, 10:56

2.2, Lecture 2.2 - Information Measures

24.09.2021, 21:26

2.1, Lecture 2.1 - Probability Review

24.09.2021, 21:11

1.2, Lecture 1.2 - Probability Review

22.09.2021, 12:54

1.1, Lecture 1.1 - Introduction

18.09.2020, 18:22

26, Lecture 26 - Review Session

18.12.2020, 11:06

25, Lecture 25 - generalization bound

14.12.2020, 10:52

24, Lecture 24 - exploration bias and generalization bound

11.12.2020, 12:12

23, Lecture 23 - compression

07.12.2020, 11:08

22, Lecture 22 - compression

04.12.2020, 10:46

21, Lecture 21 - compression

30.11.2020, 11:15

20, Lecture 20 - exponential family

27.11.2020, 12:19

19, Lecture 19 - exponential family

23.11.2020, 11:32

18, Lecture 18 - exponential family

20.11.2020, 12:10

17, Lecture 17 - Property Estimation and Exponential Family

16.11.2020, 12:43

16, Lecture 16 - property testing

13.11.2020, 12:31

15, Lecture 15 - distribution estimation

09.11.2020, 11:14

14, Lecture 14 - distribution estimation

06.11.2020, 12:14

13, Lecture 13 - multi-arm bandits, distribution estimation

02.11.2020, 11:07

12, Lecture 12 - multi-arm bandits

30.10.2020, 12:03

11, Lecture 11 - multi-arm bandits

26.10.2020, 11:41

10.1, Lecture 10.1 - detection

19.10.2020, 11:36

10.2, Lecture 10.2 - detection

19.10.2020, 11:36

9.1, Lecture 9.1 - estimation

16.10.2020, 10:46

9.2, Lecture 9.2 - estimation

16.10.2020, 10:45

8.2, Lecture 8.2 - estimation

12.10.2020, 12:20

5.1, Lecture 5.1 - signal representation

02.10.2020, 10:18

5.2, Lecture 5.2 - signal representation

02.10.2020, 10:18

4.2, Lecture 4.2 - signal representation

28.09.2020, 11:14

4.1, Lecture 4.1 - signal representation

28.09.2020, 10:08

2.2, Lecture 2.2 - information measures: part 2/2

18.09.2020, 18:37

2.1, Lecture 2.1 - information measures: part 1/2

18.09.2020, 18:30

1.2, Lecture 1.2 - Review of probability

18.09.2020, 18:24


This file is part of the content downloaded from Foundations of Data Science.

Summary

We discuss a set of topics that are important for the understanding of modern data science but that are typically not taught in an introductory ML course. In particular we discuss fundamental ideas and techniques that come from probability, information theory as well as signal processing.

Content

This class presents basic concepts of Information Theory and Signal Processing and their relevance to emerging problems in Data Science and Machine Learning.

A tentative list of topics covered is:

  1. Information Measures
  2. Multi-arm Bandits
  3. Detection and Estimation
  4. Distribution Estimation, Property Testing, and Property Estimation
  5. Exponential Families
  6. Signal Representations
  7. Compression and Dimensionality Reduction
  8. Information Measures and Generalization Error

Materials

  • Lecture Notes (Slightly updated Sept 24: Added a few more details in the proofs of the "Mutual Information" section (Section 4.5))
Additional Material:

Schedule

Note: Our Schedule deviates slightly from what is shown on IS-Academia.
  • Tuesdays:
    • 11:15-12:30, BC 01 (Lecture)
    • 12:30-13:15, Lunch Break
    • 13:15-14:30, BC 01 (Lecture)
    • 14:30-15:00, BC 01 (Solve HW Problem 1 together)
  • Wednesdays:
    • 13:15-15:00, GC B3 30 (Exercises) 
    • Exception: Wed, Sept 24: 13:15-15:00 Lecture

ED Discussion Forum

  • We will use the ED Discussion Forum for this class. Everyone is strongly encouraged to make the most of this!
    • Ask questions!
    • Answer questions!
  • The class staff will check the forum on Monday afternoon and on Thursday afternoon.


SWITCHtube Channel

We will not make new video recordings this year. You can access the videos from a couple of years ago. The content is largely the same, but the order of the topics is slightly different.

Grading

  • If you do not hand in your final exam your overall grade will be NA.
  • Otherwise, your grade will be determined based on the following weighted average: 10% for the Homework, 30% for the Midterm Exam, 60% for the Final Exam.
  • The Midterm Exam will take place on Wednesday, November 12, 2025, 13:15-15:00
  • The Final Exam will take place on at some point between January 12, 2026 and January 31, 2026.




Week 1 (Basics of Probability)

Sept 9: Introduction and Probability Review
Sept 10: Exercise Session (Homework 1)


Week 2 (Information Measures)

Sept 16: Information Measures
Sept 17: Exercise Session (Homework 2)


Week 3 (Information Measures)

Sept 23 : Information Measures
Sept 24 : Information Measures (Lecture, exceptionally)

Week 4 (Information Measures)

Sept 30: Information Measures
Oct 1: Exercise Session (Homework 2)

Week 5 (Multi-Arm Bandits)

Oct 7: Multi-Arm Bandits
Oct 8: Exercise Session (Homework 3)

Week 6 (Multi-Arm Bandits)

Oct 14: Multi-Arm Bandits
Oct 15: Exercise Session (Homework 3)


Fall Break (October 20-26)

No class, No exercise session


Week 7 (Detection & Estimation)

Oct 28: Detection and Estimation Theory
Oct 29: Exercise Session (Homework 4)


Week 8 (Distribution Estimation)

Nov 4: Distribution Estimation
Nov 5: Exercise Session (Homework 4)


Week 9 (Property Testing)

Nov 11: Property Testing
Nov 12, 13:15-15:00: Midterm Exam

Week 10 (Exponential Families)

Nov 18: Exponential Families
Nov 19: Exercise Session (Homework 5)


Week 11 (Signal Representations)

Nov 25: Signal Representations
Nov 26: Exercise Session (Homework 6)


Week 12 (Signal Representations)

Dec 2: Signal Representations
Dec 3: Exercise Session (Homework 6)


Week 13 (Compression)

December 9: Compression: Dimensionality Reduction (Random Projections), then classic data compression
December 10: Exercise Session (Homework 7)


Week 14 (Information Measures and Generalization)

December 16: Information-theoretic perspective on Generalizaton of Learning Algorithms
December 17: Exercise Session (Homework 7)