Lectures related to Coordinate descent

Coordinate Descent: Optimization Strategies

Explores coordinate descent optimization strategies, emphasizing simplicity in optimization through one-coordinate updates and discussing the implications of different approaches.

Descent methods and line search: Preconditioned steepest descent

Introduces preconditioning in optimization problems and explains steepest descent iteration.

Descent methods and line search: Inexact line search

Explores descent methods, line search, and the importance of small steps.

Convex Optimization: Gradient Algorithms

Covers convex optimization problems and gradient-based algorithms to find the global minimum.

Mathematics of Data: Computation Role

Explores the role of computation in data mathematics, focusing on iterative methods, optimization, estimators, and descent principles.

Descent Methods and Newton Method with Line Search

Covers the comparison between descent methods and Newton's method, modifications, line search, and convergence analysis.

Coordinate Descent: Efficient Optimization Techniques

Covers coordinate descent, a method for optimizing functions by updating one coordinate at a time.

Stochastic Optimization: Algorithms and Methods

Explores stochastic optimization algorithms and methods for convex problems with smooth and nonsmooth risks.

Recommender Systems: Matrix Factorization

Explores matrix factorization in recommender systems, covering optimization, evaluation metrics, and challenges in scaling.

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.

Newton's Method: Optimization Techniques

Explores optimization techniques like gradient descent, line search, and Newton's method for efficient problem-solving.

Laplace's Method: Exercises

Covers exercises related to Laplace's method and complex analysis.

Optimization Techniques: Convexity in Machine Learning

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

Quasi-Newton Methods

Introduces Quasi-Newton methods for optimization, explaining their advantages over traditional approaches like Gradient Descent and Newton's Method.

Descent methods and line search: Quadratic interpolation

Covers Newton's method and quadratic interpolation to find function minima.

Deep Learning Fundamentals

Introduces deep learning, from logistic regression to neural networks, emphasizing the need for handling non-linearly separable data.