Explores Sum of Squares polynomials and Semidefinite Programming in Polynomial Optimization, enabling the approximation of non-convex polynomials with convex SDP.
Covers Markov Chain Monte Carlo for sampling high-dimensional distributions, discussing challenges, advantages, and applications like the Knapsack Problem and cryptography.
Introduces Lasso regularization and its application to the MNIST dataset, emphasizing feature selection and practical exercises on gradient descent implementation.