Machine Learning and Computational Statistics

 

  • Statistical learning theory framework, 
  • Linear algebra and Convex optimization: stochastic gradient descent, Matrix/vector differentiation, sub-gradient descent, Singular Value Decomposition, Linear Discriminant Analysis, 
  • Regression methods: Linear and nonlinear regression, regularized regression (Lasso algorithms, ridge regression), regression with derived inputs (PCA, Partial least squares)
  • Model assessment and selection: Variance decomposition, cross-validation
  • Basis expansion: Piecewise polynomials and splines
  • Kernel smoothing methods: Kernel density estimation and classification, mixture models
  • Support Vector Machine, Decision trees,  
  • Ensemble methods: boosting and bagging, random forest, AdaBoost, 
  • Neural networks
  • Unsupervised learning: Association rules, clustering
  • Bayesian methods, hierarchical models, Gibbs sampling, Bayesian networks, class-conditional models, naïve Bayes