Schedule
This schedule should be considered tentative and subject to change, at least until it actually takes place!
In addition to the course notes, I have posted some background notes. Some material in these notes is truly background that you will have seen in prior classes. Other material may be new to you, and some of it will be covered in class. You should feel free to ask questions about any of this!
Week | Day | Date | Notes and readings | HW |
---|---|---|---|---|
1 | Tue, | Jun 12 | Introduction and optimization basics | |
Wed, | Jun 13 | Linear least squares and regularization | ||
Thu, | Jun 14 | Regularizing least squares and gradient descent | ||
Fri, | Jun 15 | Stochastic gradients, scaling, and Newton | ||
2 | Tue, | Jun 19 | Latent factor models | |
Wed, | Jun 20 | SVD and other low rank decompositions | ||
Thu, | Jun 21 | Non-negative matrix factorization | ||
Fri, | Jun 22 | Matrix completion | ||
3 | Tue, | Jun 26 | Basics of function approximation | |
Wed, | Jun 27 | Many interpretations of kernels | ||
Thu, | Jun 28 | Gaussian processes and kernel learning | ||
Fri, | Jun 29 | Scaling kernel methods | ||
4 | Tue, | Jul 03 | Matrices associated with graphs | |
Wed, | Jul 04 | Function approximation on graphs | ||
Thu, | Jul 05 | Graph clustering and partitioning | ||
Fri, | Jul 06 | Centrality measures |