Lecture

Learning the Kernel Solution: MGT-418 Tutorial

Related lectures (29)

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.

SVM - Principle: Linear Classifiers

Covers the history and applications of SVM, as well as the construction of linear classifiers and the concept of classifier margin.

Optimization Techniques: Convexity in Machine Learning

Covers optimization techniques in machine learning, focusing on convexity and its implications for efficient problem-solving.

Max-Margin Classifiers

Explores maximizing margins for better classification using support vector machines and the importance of choosing the right parameter.

Optimization with Constraints: KKT Conditions

Covers the KKT conditions for optimization with constraints, essential for solving constrained optimization problems efficiently.

Convex Sets: Mathematical Optimization

Introduces convex optimization, covering convex sets, solution concepts, and efficient numerical methods in mathematical optimization.

Linear Programming: Weighted Bipartite Matching

Covers linear programming, weighted bipartite matching, and vertex cover problems in optimization.

Optimization Techniques: Convexity and Algorithms in Machine Learning

Covers optimization techniques in machine learning, focusing on convexity, algorithms, and their applications in ensuring efficient convergence to global minima.

Convex Optimization Tutorial: KKT Conditions

Explores KKT conditions in convex optimization, covering dual problems, logarithmic constraints, least squares, matrix functions, and suboptimality of covering ellipsoids.

Convex Optimization: Exercises

Covers exercises on convex optimization, focusing on formulating and solving optimization problems using YALMIP and solvers like GUROBI and MOSEK.

Faster Gradient Descent: Projected Optimization Techniques

Covers faster gradient descent methods and projected gradient descent for constrained optimization in machine learning.

Convexifying Nonconvex Problems: SVM and Dimensionality Reduction

Explores convexifying nonconvex problems through SVM and dimensionality reduction techniques.

Legendre Transform

Explores the Legendre transform, duality in convex analysis, and optimization problems.

Convex Optimization: Introduction and Sets

Covers the fundamentals of convex optimization, including mathematical problems, minimizers, and solution concepts, with an emphasis on efficient methods and practical applications.

Support Vector Machines

Introduces Support Vector Machines, covering Hinge Loss, hyperplane separation, and non-linear classification using kernels.

Linear Models for Classification

Covers linear models for classification, including SVM, decision boundaries, support vectors, and Lagrange duality.

KKT for convex problems and Slater's CQ

Covers the KKT conditions and Slater's condition in convex optimization problems.

The Hidden Convex Optimization Landscape of Deep Neural Networks

Explores the hidden convex optimization landscape of deep neural networks, showcasing the transition from non-convex to convex models.

Optimization Methods: Convergence and Trade-offs

Covers optimization methods, convergence guarantees, trade-offs, and variance reduction techniques in numerical optimization.

KKT and Convex Optimization

Covers the KKT conditions and convex optimization, discussing constraint qualifications and tangent cones of convex sets.