MVE188 / MSA102 Computational methods for Bayesian statistics Autumn 25
Course PM
This page contains the program for the course. Other information, such as learning outcomes, teachers, literature, examination, and old exams is in a separate course PM.
Program
The schedule is in TimeEdit and in the table below. Lectures, on Mondays 15:15-17:00 and Wednesdays 10:00-11:45 in Pascal, will be traditional lectures, with students asking questions and some student activities. What to read before the lecture will be listed below, and overheads used will be available below (shortly) before each lecture. Wednesdays 8:00-9:45 in MVF33 will be exercise classes, with demonstrations of solutions of exercises in a list given below. Thursdays 13:15-15:00 will be student-initiated activities: Some possibilities are
- students work alone or in groups, and the teacher is available for questions,
- students pose general or specific questions, and we work through these together,
- any other learning activities that students propose (which we then organize together)
Study guide
The course PM contains a list of textbooks which you should use to prepare BEFORE each lecture. Rather than reading all of them, you should use material from the book or books that suit your background and style of learning. Murphy (denoted M below) is a quite advanced book, containing basically all material we go through and very much more. It may be useful as a reference. Bishop (B) is also advanced, but slightly easier to read. It also contains exercises, which Murphy does not. Albert (A) is an introductory book, with focus on practical Bayesian modelling and computation using R. It may be a useful learning tool for some. Robert & Casella (RC) and Särkää (S) may be referred to at some points, for specific material.
The list of lectures below will contain, for each lecture, references to the relevant parts of the textbooks. It will also contain (posted shortly before the lecture) overheads ane example code used.
The lectures are not recorded. A few years back (mostly in connection with the pandemic) lectures were recorded. Here is a list of recordings from 2023; note however that the sequence of subjects has changed, even if the overall contents is mostly the same.
Schedule
Contents | Study material / activity |
Time and place |
Lecture 1: The Bayesian paradigm. Course introduction. |
M: 2.1, 2.2, 3.2. B: 2.1, 2.2, 2.3, 2.4. A: 2, 3, 4. Overheads. |
Monday 1/9, 15:15 - 17:00, Pascal. |
Exercise class (demonstration/discussion of exercises) |
Old exams: 2023-08-24: q1. 2020-10-26: q1. A: 1.6: q4, q5. 2.9: q1, q2. R code |
Wednesday 3/9, 8:00 - 9:45, MVF33. |
Lecture 2: Using conjugacies in exponential families of distributions |
M: 2.4, 3.4. B: 2.1, 2.2, 2.3, 2.4. A: 2, 3, 4. Overheads. R code. |
Wednesday 3/9 10:00 - 11:45, Pascal. |
Student-initiated activities / workshop |
For example, reviews based on student requests, e.g., about how to use R. Going through last overheads in Lecture 1. Student work on exercises. |
Thursday 4/9, 13:15 - 15:00, MVF26. |
Lecture 3: Graphical Networks. |
Monday 8/9, 15:15 - 17:00, Pascal. | |
Exercise class (demonstration/discussion of exercises) |
Old exams: 2024-08-29: q4. 2024-10-26: q3. 2024-01-05: q2. 2025-01-09: q4. 2924-01-05: q8. 2021-01-05: q1. |
Wednesday 10/9, 8:00 - 9:45, MVF33. |
Lecture 4: Basic Bayesian inference and modelling. |
Review uncovered material from Lectures 3 and 2, and then continue with new overheads. R code. |
Wednesday 10/9 10:00 - 11:45, Pascal. |
Student-initiated activities / workshop |
|
Thursday 11/9, 13:15 - 15:00, MVF26. |
Lecture 5: Information theory. |
B: 1.2.4, 1.6. M: 2.3, (2.7). Overheads. Start with finishing material from Lecture 4. |
Monday 15/9, 15:15 - 17:00, Pascal. |
Exercise class (demonstration/discussion of exercises) |
Old exams: 2025-01-09 q2. 2024-08-29 q1. 2024-01-05 q5. 2022-01-05 q6. 2021-10-30 q5. 2021-01-05 q4. |
Wednesday 17/9, 8:00 - 9:45, MVF33. |
Lecture 6: Types of approximate inference. |
|
Wednesday 17/9 10:00 - 11:45, Pascal. |
Student-initiated activities / workshop |
|
Thursday 18/9, 13:15 - 15:00, MVF26. |
Lecture 7: Point estimates. The EM algorithm. The Laplace approximation. |
|
Monday 22/9, 15:15 - 17:00, Pascal. |
Exercise class (demonstration/discussion of exercises) |
Old exams: 2025-01-09 q6. 2024-10-26 q5. 2024-08-29 q5. 2023-08-24 q5. |
Wednesday 24/9, 8:00 - 9:45, MVF33. |
Lecture 8: Simulation methods. Markov chains. |
|
Wednesday 24/9 10:00 - 11:45, Pascal. |
Student-initiated activities / workshop |
|
Thursday 25/9, 13:15 - 15:00, MVF26. |
Deadline first obligatory hand-in |
|
Friday 26/9 16:00. |
Lecture 9: Markov chain Monte Carlo. Gibbs sampling. |
|
Monday 29/9, 15:15 - 17:00, Pascal. |
Exercise class (demonstration/discussion of exercises) |
Old exams: 2025-01-09 q1. 2024-10-26 q1 & q2. 2024-08-29 q2. |
Wednesday 1/10, 8:00 - 9:45, MVF33. |
Lecture 10: Hamiltonian Monte Carlo. |
|
Wednesday 1/10 10:00 - 11:45, Pascal. |
Student-initiated activities / workshop |
|
Thursday 2/10, 13:15 - 15:00, MVF26. |
Lecture 11: State space models and Hidden Markov Models. Kalman filters. |
|
Monday 6/10, 15:15 - 17:00, Pascal. |
Exercise class (demonstration/discussion of exercises) |
Old exams: 2025-01-09 q3. 2024-08-29 q3 & q6. 2023-10-28 q4. 2021-10-30 q6 |
Wednesday 8/10, 8:00 - 9:45, MVF33. |
Lecture 12: Kalman filters. Particle filters. Viterbi. |
|
Wednesday 8/10 10:00 - 11:45, Pascal. |
Student-initiated activities / workshop |
|
Thursday 9/10, 13:15 - 15:00, MVF26. |
Deadline second obligatory hand-in |
|
Friday 10/10, 16:00. |
Lecture 13: Variational Bayes. |
|
Monday 13/10, 15:15 - 17:00, Pascal. |
Exercise class (demonstration/discussion of exercises) |
Old exams: 2024-10-26 q4. 2022-10-29 q5. 2025-10-09 q5. 2024-01-05 q7. |
Wednesday 15/10, 8:00 - 9:45, MVF33. |
Lecture 14: Decision theory. ABC. |
|
Wednesday 15/10 10:00 - 11:45, Pascal. |
Student-initiated activities / workshop |
|
Thursday 16/10, 13:15 - 15:00, MVF26. |
Lecture 15: Review |
Review |
Monday 21/10, 15:15 - 17:00, Pascal. |
WRITTEN EXAM |
Everything |
Thursday 30/10, 14:00 - 18:00. |
Recommended study questions, in addition to those listed for exercise sessions.
After the lecture whose number is on the left, you may work on the questions listed in that line.
The list below is in the process of being updated.
OLD EXAMS | Exercises from textbooks, or independently written | |
1 |
2024-01-05 q1. 2022-01-05 q1. |
|
2 |
2023-01-05 q1.2021-10-30 q1. 2020-10-29 q6. |
A2.9: 4,5; A3.9: 1,3 some solutions. |
3 | 2023-10-28 q6 & q7. 2023-08-24 q4. 2023-01-05 q4 & q7. 2022-08-25 q4 & q5. 2022-01-05 q7. 2021-08-26 q4. |
A3.9: 4; solutions. Some exercises; corresponding solutions |
4 |
2023-10-28 q1 & q2. 2023-08-24 q3. 2022-10-29 q1. 2022-08-25 q2. 2020-10-29 q2. |
A4.8 1,4,7. solutions.
|
5 |
|
|
6 |
|
|
7 |
2022-10-29 q4 & q6. 2022-08-25 q7. 2021-08-26 q3. |
|
8 |
2024-01-05 q3. 2023-08-24 q2. 2022-10-29 q2. 2021-08-26 q2. |
RC 2.11, 2.12, 2.18, 2.22. some solutions. |
9 |
2024-01-05 q4 & q6. 2023-10-28 q3. 2023-10-05 q2. 2022-29 q3. 2022-08-25 q1. 2022-01-05 q2 & q4. 2021-10-30 q2 & q3. 2021-08-26 q6. 2021-01-05 q2 & q3. 2020-10-29 q3 & q4. |
A7.13: 1,2. A5.13: 1,5. A6.13: 1,2. solutions A5.13: 2; A6.13: 3; A10.7: 6. A9.7: 3,4; solutions A9.7: 6; A10.7: 5, 7. solutions |
10 |
2023-01-05 q3. 2022-08-25 q3. 2021-10-30 q4. 2020-10-29 q5. |
|
11 |
2021-01-05 q5. |
|
12 |
2023-01-05 q6. |
|
13 |
2023-10-28 q5. 2023-08-24 q6. 2022-08-25 q6. 2022-01-05 q8. |
|
14 |
2021-08-26 q1. 2021-01-05 q7. 2020-10-29 q7. |
Course work
To understand and learn the methods of this course, it is essential to work with examples on a computer, in addition to working with the study material and doing theoretical exercises. Our textbooks contain a large number of exercises, for both theoretical and computer solutions, and some exercises are listed above.
As an obligatory part of the course, each student must do 2 assignments. The deadlines for these are Friday 26 September at 16:00 and Friday 10 October at 16:00. Details about the assignments will be available from the links at the bottom of this page. Answers must also be handed in via Canvas. Although students are welcome to cooperate in their work, each student must be prepared to explain orally all details of their own written answers.
As much of the course material uses the R language for examples and illustrations, students should also use this language. Students who are not familiar with this language need to study it individually during the first weeks of the course. See, for example, the introductory chapters of our textbooks.
If you have problems with getting started with the course, or for example getting started with R, please do not hesitate to contact me. I hope that we can have active communication during the course. In addition to contact at lectures and exercise sessions, you may contact me on canvas or by mail at mostad@chalmers.se. I usually answer within a day or so.
Course summary:
Date | Details | Due |
---|---|---|