Coursework pertaining to CS6230 : Optimization Methods in Machine Learning offered in Fall 2017

• Convex Sets and Functions
• Properties of (Quasi)Convex/Concave Functions

• Plotting special functions
• Experimenting with Gradient Descent with different step size setting schemes

• Subgradient calculus and properties
• Proximal gradient descent based proofs

• Partly theoretical as well: Karush-Kuhn-Tucker conditions, Strong convexity, Dual Formulation
• Cost Sensitive SVM in CVXPY

• LaTeX script for generating the slides used for presenting the paper Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information by Peng Xu, Farbod Roosta-Khorasani and Michael W. Mahoney

• Empirical study of benefits of Adaptive Gradient Methods
• Mostly inspired by The Marginal Value of Adaptive Gradient Methods in Machine Learning by Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern, Nathan Srebro and Benjamin Recht