STA 7934: Advanced Regression
Lecture. 10:40 AM - 12:35 PM (Tues) 10:40 AM - 11:30 AM (Thurs)
Instructor. Aaron Molstad (amolstad@ufl.edu), 202 Griffin-Floyd
Virtual office hours. 3:30 PM - 5:30 PM (Wed) [Zoom link]
In-person/virtual office hours. 11:40 AM - 12:40 PM (Thurs) [Zoom link]
Syllabus. [pdf] Lecture link. [link]
Note that you must be logged into your UFL eLearning account to access course materials.
| Lecture | Topics | |||
| 0 (8/24) | Syllabus, ordinary least squares, ridge regression [slides] | |||
| 1 (8/26) | Ridge regression, cross-validation [slides] | |||
| 2 (8/31) | Lasso motivation and computation [slides] | |||
| 3 (9/2) | LARS algorithm, variants of the lasso [slides][lecture] | |||
| 4 (9/7) | Statistical properties of lasso [slides][lecture] | |||
| 5 (9/9) | Support recovery for lasso [slides][lecture] |
Note that Lectures 0-2 have been removed from the eLearning site due to reaching our storage capacity. If you would like the recorded lecture, please email me and I will send you the .mp4 file.
Linear regression notes [pdf]
Homework 1 (Due Friday, September 17th at 5:00pm)[pdf][submission]
| 6 (9/14) | Basis expansions and splines [slides][lecture] | |||
| 7 (9/16) | Smoothing splines [slides][lecture] | |||
| 8 (9/21) | RKHS, Representer Theorem [slides][lecture] | |||
| 9 (9/23) | Kernels, kernel ridge regression [slides][lecture] |
Semiparametrics notes [pdf]
Homework 2 (Due Friday, October 1st at 5:00pm) [pdf][submission]
| 10 (9/28) | Nearest-neighbors regression, kernel smoothers, LDA [slides][lecture] | |||
| 11 (9/30) | Discriminant analysis [slides][lecture] | |||
| 12 (10/5) | Separating hyperplanes and SVMs [slides][lecture] | |||
| 13 (10/7) | Generalizations of SVMs [slides]][lecture] |
Classification notes [pdf]
Homework 3 (Due Friday, October 15th at 5:00pm) [pdf][submission]
Project proposal (Due Monday, October 18th at 5:00pm)[submission]
| 14 (10/12) | Generalized additive models [slides][lecture] | |||
| 15 (10/14) | Regression trees [slides][lecture] | |||
| 16 (10/19) | Bagging, random forests, boosting [slides][lectures] |
Generalized additive model notes[pdf]
Tree-based methods notes[pdf]
Homework 4 (Due Friday, October 29th at 5:00pm) [pdf][submission]
| 17 (10/26) | Boosting [slides][lecture] | |||
| 18 (10/28) | Ensemble methods [slides][lecture] | |||
| 19 (11/2) | Neural networks [slides][lecture] | |||
| 20 (11/4) | Fitting neural networks [slides][lecture] | |||
| 21 (11/9) | Double descent [slides][lecture] |
Homework 5 (Due Friday, November 12th at 5:00pm)[pdf][submission]
| 22 (11/16) | Graphical models [slides][lecture] | |||
| 23 (11/18) | Graphical models continued [slides][lecture] | |||
| 24 (11/30) | Multivariate response regression [slides][lecture] |
| 25 (12/2) | Multivariate response regression continued [slides][lecture] |
Project progress report (Due Tuesday, November 23rd at 5:00pm) [submission]
Homework 6 (Due Tuesday, December 14th at 5:00pm) [pdf][submission]
[Presentation #1][Presentation #2][Presentation #3][Presentation #4]
[Presentation #5][Presentation #6][Presentation #7][Presentation #8]
[Presentation #9]
Project presentation (Due Monday, December 6th at 5:00pm) [submission]
Presentation feedback (Due Friday, December 10th at 5:00pm) [submission]
Project report (Due Thursday, December 16th at 12:00pm) [submission]