Events

11/26/
2018
Monday
4:15pm
University of Göttingen
Nanostatistics

Conventional light microscopes have been used for centuries for the study of small length scales down to about 250 nanometers. At such a resolution level images are  blurred and noisy and the data often can be well approximated by a Gaussian or Poisson model. 

12/03/
2018
Monday
4:15pm
University of California, Berkeley
Machine Learning: Dynamical, Economic and Stochastic Perspectives
While there has been significant progress in the theory and practice in machine learning in recent years, many fundamental challenges remain.  
12/10/
2018
Monday
4:15pm
MIT
TBA
12/11/
2018
Tuesday
4:00pm
University of Chicago
Learning from Highly Correlated Features using Graph Total Variation

Sparse models for machine learning have received substantial attention over the past two decades. Model selection, or determining which features are the best explanatory variables, is critical to the interpretability of a learned model.