Statistical Machine Learning Reading Group
Carnegie Mellon University
Room: 6501 Gates-Hillman CenterTime: 4:30-5:30 pm Thursday
| SCHEDULE: |
|
| Sept 1 |
The Benefit of Group Sparsity (arXiv) Authors: Junzhou Huang, Tong Zhang Presenter: Min Xu |
| Sept 8 |
Neyman-Pearson classification, convexity and stochastic constraints (paper) Authors: Philippe Rigollet and Xin Tong Presenter: Sivaraman Balakrishnan |
| Sept 15 |
Calibrated Forecasters Authors: Misc Presenter: Aaditya Ramdas |
| Sept 22 |
Spectral Methods for Learning Multivariate Latent Tree Structure (arXiv) Authors: Animashree Anandkumar, Kamalika Chaudhuri, Daniel Hsu, Sham M. Kakade, Le Song, Tong Zhang Presenter: Ankur Parikh |
| Oct 6 |
High-dimensional regression with noisy and missing data: Provable
guarantees with non-convexity (arXiv) Authors: Po-Ling Loh and Martin J. Wainwright Presenter: Akshay Krishnamurthy |
|
Oct 20 Note: 2:30-4:00 pm |
Guest: Robert Tibshirani |
| Oct 27 |
Cross validation is risk consistent for lasso Authors: Darren Homrighausen and Dan McDonald Presenter: Darren Homrighausen and Dan McDonald |
| Nov 3 |
Presenter: Martin Azizyan |
| Nov 10 |
Presenter: James Sharpnack |
| Nov 17 |
Approximation of Functions of Few Variables in High Dimensions (pdf) Author: Ronald DeVore, Guergana Petrova, Przemyslaw Wojtaszczyk Presenter: Ina Fiterau |
Reading list requests/suggestions:
- Rademacher Complexities and Bounding the Excess Risk in Active Learning by Vladimir Koltchinskii pdf
- PAC-Bayesian Analysis of Co-clustering and Beyond by Y. Seldin and N. Tishby pdf
Past reading: Summer 11, Spring 11, Fall 10