6.437 Inference and Information
Spring 2019
Reverend Thomas Bayes, Sir Ronald Fisher, and Claude Shannon
Instructors: Polina Golland, Gregory W Wornell
TAs: Igor Spasojevic, Chandler B Squires, Matthew Staib, Jennifer Susan Tang
Lecture:
Tuesdays and Thursdays, 9:30-11am
(32-123)
Recitation: Fridays, 1-2pm or 2-3pm
(4-163)
TA Office Hours: Mondays 4-6pm and Thursdays 4:30-5:30pm
(34-304)
Greg's and Polina's Office Hours: By Appointment
Information:
Introduction to principles of Bayesian and non-Bayesian statistical inference. Hypothesis testing and parameter estimation, sufficient statistics; exponential families. EM algorithm. Log-loss inference criterion, entropy and model capacity. Kullback-Leibler divergence and information geometry. Asymptotic analysis and large deviations theory. Model order estimation; nonparametric statistics. Computational issues and approximation techniques; Monte Carlo methods. Selected special topics including universal inference and learning, and universal features and neural networks.
ACCESS TO THE WEBSITE is limited to the students enrolled in the course as LISTENERS or FOR CREDIT. Please talk to us in class about registering and getting access to the web site. You can download the general information handout by clicking on the "General Info" tab on the left, even if you are not enrolled in the course.
Announcements
Welcome to 6.437!
We will use PIAZZA for discussion and announcements this semester.Announced on 04 February 2019 6:00 p.m. by Polina Golland
