2–7 Jun 2019
Hotel Ariston, Paestum
Europe/Rome timezone

Scientific Programme

Probability theory

  • Introduction to probability theory (axioms, Pascal and birthday problems), random variables, probability functions (mass and density functions), probability distributions, moments (mean, variance), correlation, covariance, and independence
  • Distribution of functions of random variables (mostly sums)
  • Conditional probability, Bayes theorem, representation theorem, derivation of binomial distribution, derivation of Poisson distribution from binomial and from a birth process

Statistical inference

  • Parameter estimates, properties of estimators
  • Maximum likelihood method
  • Pearson and Neyman chi-squares

Hypothesis testing and interval estimation

  • hypothesis tests
  • asymptotic formulae for upper limits and significance evaluation
  • treatment of nuisance parameters
  • the look-elsewhere effect

Statistical software tools

  • Overview of the main statistical tools
  • RooFit, RooStats
  • Hands-on exercises

Multivariate analysis

  • Introduction to multivariate analysis
  • Supervised learning: classification and regression
  • The bias-variance decomposition
  • Optimism, information criteria and cross-validation
  • The modelling process: exploratory data analysis, feature engineering and model tuning

Machine learning

  • Artificial Neural Networks
  • Deep Learning
  • Hands-on session: hackaton

Lecturers:

  • Glen Cowan, Royal Holloway, University of London
  • Sergei Gleyzer, University of Florida
  • Eilam Gross, Weizmann Institute of Science
  • Mario Pelliccioni, INFN Torino
  • Harrison Prosper, Florida State University, Tallahassee
  • Aldo Solari, University of Milano-Bicocca