Units: 3
This course will provide senior undergraduate and graduate students an introduction to mathematical nonlinear optimization with applications in machine learning and data science. This course will involve analysis of optimization algorithms, in particular, scalability of algorithms to large datasets will be discussed in theory and in implementation. The fundamental algorithms for nonlinear optimization are studied and applied to supervised learning models, including but not limited to nonlinear regression, logistic regression, support vector machines, and deep neural networks. Students will write their own implementation of the algorithms in the MATLAB/Python programming language and explore their performance on realistic data sets. May be convened with SIE 449.
Prerequisite(s): SIE 270, SIE 305, SIE 340
Usually offered: Spring