top of page

Information Theory & Coding (High-dimensional Statistics)
Fall 2018

Title
Topic
Lecture 13

Bayesian CR lower bound, information bound, local estimators, biased estimators

Lecture 14

maximum likelihood estimator, high-dimensional unstructured estimation, bowl-shaped loss

Lecture 15

two-point quantization of the estimation problem (LeCam’s method)

Lecture 16

two-point per dimension (coordinate) quantization of the estimation problem (Assouad's method)

Lecture 17

information-theoretic method to analyzing risk; model capacity, geometric interpretation

Lecture 18

Shannon's method, Fano's method

Lecture 19

structured high-dimensional estimation, denoising a sparse vector (lower bound)

Lecture 20

denoising a sparse vector (upper bound); thresholding schemes for sparse recovery

Lecture 21

linear regression and sparse recovery

Lecture 22

functional estimation (lower bounds)

Lecture 23

functional estimation (upper bounds)

bottom of page