Presentations
Here are my presentations in the Machine Learning session, which is held for ISS students in ECE Department of Boston University :
- Poster : An Impossibility Result for High Dimensional Supervised Learning (1st May 2013) : This is a poster version of the my results on distribution dependent impossibility of learning in high dimensions. It was presented in the New England Machine Learning Day at Microsoft Research Cambridge MA.
- Slides : An Impossibility Result for High Dimensional Supervised Learning (12 Apr. 2013) : This presentation is some of my results on distribution dependent impossibility of learning in a high dimensional setting.
- Slides : Fully Efficient Nonnegative Matrix Factorization (14 Dec. 2012) : This presentation is some rephrasing of the 5th section of the following paper : Arora, S., Ge, R., Kannan, R., and Moitra, A., ”Computing a nonnegative matrix factorization, provably,” In ACM Symposium on Theory of Computing (STOC), 2012.