CS724 Topics in Algorithm Theory and Design: Fall 2016
This offering of cs724 is dedicated to a presentation of optimization algorithms in machine learning and data mining. This course requires a background in linear algebra, topology, and functional analysis. We will discuss such topics as regression, support vector machines, clustering, differential privacy, etc.. This will be supplemented by a presentation of several special topics that you did not see in the typical mathematics course, such as various types of normed and metric spaces, Banach and Hilbert spaces, convexity, optimization techniques, etc.
Taking this course may help significantly with your research work; for this reason, the course is intended to attract mainly doctoral students.
Here is a list of topics that I intend to cover:
|
Norms and linear normed spaces |
Convex Sets |
|
Differentiation |
Convex Functions |
|
Banach and Hilbert Spaces |
Constrained and Non-constrained Optimization |
|
Regression |
Support Vector Machines |
|
Differential Privacy |
|
The main reference for this are several handouts that will be posted on my web page www.cs.umb.edu/~dsim. Bibliography will be indicated at the end of each topic; however, your main sources are these lectures and the slides and handouts that will be posted on my web page.
No late homeworks will be accepted.
Download and install R and R Studio for your operating system version. We will use R as auxiliary software.
Handouts will be posted here:
Homeworks will be posted here:
Grades in this course will be based on homework, a take-home examination, and class participation.