LM in Data Science
STATISTICAL LEARNING
The Goal: expose you to a variety of (statistical) methods and models and give you a flavor of some interesting theoretical results, under different assumptions, that support and clarify their practical relevance and performance.
Prerequisites:all the topics covered in Stat4DS Part I, the basics of Linear Algebra and Calculus, and a data-analytic oriented knowledge of at least one programming language.
Some of the topic we will cover (not necessarily in order):
Prerequisites:all the topics covered in Stat4DS Part I, the basics of Linear Algebra and Calculus, and a data-analytic oriented knowledge of at least one programming language.
Some of the topic we will cover (not necessarily in order):
- Review of basic probability and inference + Concentration of measure + basics of convex analysis.
- Statistical functional: bootstrap & subsampling.
- (Non)parametric Regression and Density estimation: kernels and RKHS.
- (Non)parametric Classification.
- Nonparametric Clustering: k-means, density clustering.
- Graphical Models and their applications: parametric and nonparametric approaches.
- Hints of Nonparametric Bayes
- Minimaxity & Sparsity Theory
- Docente: Pierpaolo Brutti