Course Websites

Subject offerings of new and developing areas of knowledge in electrical and computer engineering intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: May be repeated in the same or separate terms if topics vary.

Prerequisites: Maturity with probability theory at the level of ECE 534 or Math 561. ECE 563 will NOT be required. The goal of this course is to understand the fundamental limits of high-dimensional statistical problems via information-theoretic methods. We will discuss foundational topics on information-theoretic methods, such as information measures, Fano's inequality, Le Cam's method and generalizations, metric entropy and volumetric methods, aggregation, as well as their applications on specific problems, such as sparse linear regression, estimating high-dimensional matrices, principal component analysis, functional estimation, statistical estimation on large alphabets and large graphs, etc.

The goal of this course is to understand the fundamental limits of high-dimensional statistical problems via information-theoretic methods. We will discuss foundational topics on information-theoretic methods, such as information measures, Fano's inequality, Le Cam's method and generalizations, metric entropy and volumetric methods, aggregation, as well as their applications on specific problems, such as sparse linear regression, estimating high-dimensional matrices, principal component analysis, functional estimation, statistical estimation on large alphabets and large graphs, etc.