MC 2024

Lecturers and Seminarists

Lecturer	Samsonov Sergey	[svsamsonov@hse.ru]	T902
Seminarist	Ilya Lewin	[ivlevin@hse.ru]	T926

About the course

This page contains materials for Markov Chains course in 2024/2025 year, mandatory one for 1st year Master students of the MML program (HSE and Skoltech).

Link to telegram chat: https://t.me/+OJQ1vl3EmhQ3ZDRi

Grading

The final grade consists of 4 components (each is non-negative real number from 0 to 10, without any intermediate rounding) :

• O_HW for the hometasks
• O_Mid-term for the midterm exam
• O_Exam for the final exam
• O_Bonus for bonus tasks

The formula for the final grade is

• O_Final = 0.35*O_HW + 0.3*O_Mid-term + 0.35*O_Exam + 0.1*O_Bonus

with the usual (arithmetical) rounding rule.

[... Table with grades]

Lectures

• Lecture №1, 09.11
• [... Lecture №2, 18.11]
• Lecture №3, 25.11
• Lecture №4, 02.12
• Lecture №5-6, 16.12
• Lecture №7, 13.01
• Lecture №8, 20.01

Seminars

https://disk.yandex.ru/d/cXeyH_vL3fEb_g

Homeworks

To submit homework, join Google classroom — invite code da3g4oh

Homework solution file should be readable and well-organized.

• Homework 1: Deadline 13.01.2024, 23:59
• Homework 2: Deadline 03.02.2024, 23:59
• Homework 3: Deadline 17.03.2024, 23:59
• Homework 4: Deadline 23.03.2024, 23:59

Exam

TBD

Midterm

TBD

Recommended literature (1st term)

• http://www.statslab.cam.ac.uk/~james/Markov/ - Cambridge lecture notes on discrete-time Markov Chains
• https://link.springer.com/book/10.1007%2F978-3-319-97704-1 - book by E. Moulines et al, you are mostly interested in chapters 1,2,7 and 9 (book is accessible for download through HSE network)
• https://link.springer.com/book/10.1007%2F978-3-319-62226-2 - Stochastic Calculus by P. Baldi, good overview of conditional probabilities and expectations (part 4, also accessible through HSE network)
• https://elearning.unimib.it/pluginfile.php/583708/mod_resource/content/1/1-conditional-law.pdf - Probability kernels and (regular) conditional probabilities, to the third lecture.

Useful links

Energy based models:

• Tutorial from seminar: https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial8/Deep_Energy_Models.html
• Important work on EBM: https://openai.com/research/energy-based-models
• Other EBM related works of the same author: https://energy-based-model.github.io/Energy-based-Model-MIT/
• Another tutorial on EBM from CVPR 2021: https://energy-based-models.github.io/
• Another tutorial on EBM from Yann LeCun: https://www.cs.toronto.edu/~vnair/ciar/lecun1.pdf
• Comparisson between generative models: https://arxiv.org/pdf/2103.04922.pdf