The CUNY Data Science and Applied Topology Reading Group is joint between the Mathematics and Computer Science programmes. We used to meet Fridays 11.45 -- 12.45 in GC 4419. You can contact us at firstname.lastname@example.org.
Our plan is to primarily read and discuss seminal papers in data science, in applied topology and in topological data analysis. Each seminar one participant takes the responsibility to present a paper and prepare items for discussion. We expect occasionally to be able to invite external speakers.
Fall 2020 Seminar Plans
We will run a reading group in Machine Learning, reading "Understanding Machine Learning: from Theory to Algorithms" by Shalev-Schwarz and Ben-David. Seminar runs over Zoom, Fridays 12-13. Login details will be distributed on the seminar mailing list.
One good source on background material is Mathematics for Machine Learning.
Current schedule can be found here.
We will be sending out announcements through a mailing list; you can subscribe here.
- Mikael Vejdemo-Johansson, Computer Science Programme, CUNY Graduate Center; Department of Mathematics, CUNY College of Staten Island
- Azita Mayeli, Mathematics Programme, CUNY Graduate Center; Department of Mathematics, CUNY Queensborough Community College
- Vincent Martinez, Department of Mathematics and Statistics, CUNY Hunter College
We have compiled a list of papers that might be interesting to present.
Machine Learning Reading Group
Introduction to Machine Learning (Chapter 2)
Machine Learning Reading Group: A gentle start
Foundations: Chapter 2
Machine Learning Reading Group: A Formal learning model
Foundations: Chapter 3
Machine Learning Reading Group: Learning via uniform convergence
Machine Learning Reading Group: The bias-complexity tradeoff
Chapter 5 (with proofs)
Machine Learning Reading Group: The VC dimension
Chapter 6 (with proofs)
Machine Learning Reading Group: Nonuniform learnability
Machine Learning Reading Group: Linear predictors
Machine Learning Reading Group: Boosting
Machine Learning Reading Group: Model selection and validation