Teaching

Statistical Learning and Inference – SDS 323

The University of Texas at Austin · Fall 2019 & Fall 2020 · ~50 students

I designed and taught this course twice as a PhD student, introducing upper-level undergraduates to ideas of statistical learning and predictive modeling from statistical, theoretical, and computational perspectives.

Topics covered:

• Regression and classification (linear models, logistic regression, LDA/QDA)
• Model selection, regularization, and cross-validation (ridge, lasso, PCR)
• Tree-based methods and ensemble learning (CART, random forests, boosting)
• Unsupervised learning (PCA, k-means and hierarchical clustering)
• Introduction to Bayesian reasoning and probabilistic modeling

All course materials – lecture slides, problem sets, and R code – are publicly available at giorgiopaulon.github.io/SDS323.