Convexifying Nonconvex Problems: SVM and Dimensionality Reduction

About
Privacy
Disclaimer

Graph Chatbot

Related lectures (28)

Page 3 of 3

Convex Optimization: Dual Cones

Explores dual cones, generalized inequalities, SDP duality, and KKT conditions in convex optimization.

Support Vector Machines: Maximizing Margin

Explores Support Vector Machines, maximizing margin for robust classification and the transition to soft SVM for non-linearly separable data.

Support Vector Machines: SVM Basics

Covers the basics of Support Vector Machines, focusing on hard-margin and soft-margin formulations.

Projected Gradient Descent

Explores convex constrained optimization through Projected Gradient Descent, focusing on tangent space and iterative minimization.

Stochastic Gradient Descent: Non-convex Optimization Techniques

Discusses Stochastic Gradient Descent and its application in non-convex optimization, focusing on convergence rates and challenges in machine learning.

Optimization Problems: Path Finding and Portfolio Allocation

Covers optimization problems in path finding and portfolio allocation.

Conjugate Duality: Understanding Convex Optimization

Explores conjugate duality in convex optimization, covering weak and supporting hyperplanes, subgradients, duality gap, and strong duality conditions.

Learning the Kernel: Convex Optimization

Explores learning the kernel function in convex optimization, focusing on predicting outputs using a linear classifier and selecting optimal kernel functions through cross-validation.