Mth 566 Optimization for Data Science

Comprehensive study of basic optimization theory and numerical algorithms with applications to data science. Covers core concepts of convex optimization, including convexity, Lagrange multipliers, and duality theory, as well as a range of algorithms for convex and nonconvex settings with emphasis on convergence analysis. Focuses on practical applications to data science, including the analysis of machine learning models and neural network architectures. Designed to provide a solid foundation for advanced studies and research in optimization and data science.

Credits

3

Slash Listed Courses

Also offered for undergraduate-level credit as Mth 466 and may be taken only once for credit.

Prerequisite

Completion of Introduction to Linear Algebra (Mth 261) or an equivalent course, along with basic proficiency in Python.