Modelos Aleatorios en Alta Dim

Stochastic Models in High Dimensions 

Announcements and other information about the class can be found here.

Instructor: Anastasios Matzavinos, amatzavinos@mat.uc.cl 

Class meeting times: Mon & Wed 10:00 am - 11:20 am in room BC 23. 

Instructor's office hours: Wed 11:30 am - 12:30 pm or by appointment.

Course description: IMT 3420 is focused on  the various tools and techniques of high-dimensional probability along with their applications in data science and statistical learning. Topics covered include basic concentration inequalities, concentration of measure via entropic techniques and isoperimetric inequalities, random matrices, random projection methods, generic chaining, VC dimension, and the Rademacher complexity. Various applications in statistical learning will be considered, including sparse linear models in high dimensions, graphical models for high-dimensional data, non-parametric estimation, and approximation by neural networks.

The official UC course description for IMT 3420 can be found here.

Grading policy: The final grade will be based on attendance (5% of the grade), homework assignments (25%), a mid-term exam (35%),  and a final take-home exam (35%).

Homework assignments: Homework problems will be handed out on a regular basis. Discussion of homework assignments with other students is encouraged, but what is handed in should be your own work. 

References: The following references will be used in various parts of the course. 

  • R. Vershynin. High-Dimensional Probability: An Introduction with Applications in Data Science. Cambridge University Press, 2018.
  • J. Wainwright. High-Dimensional Statistics: A Non-Asymptotic Viewpoint. Cambridge University Press, 2019.
  • L. Devroye, L. Györfi, and G. Lugosi. A Probabilistic Theory of Pattern Recognition. Springer, 1996.

Announcements and other information about the class can be found here. A PDF copy of the course program can be found here: IMT_3420.pdf

Resumen del curso:

Fecha de entrega Detalles Hora de entrega