[Statlist] Reminder: ETH Young Data Science Researcher Seminar Zurich, Virtual Seminar by Ramya Korlakai Vinayak, University of Wisconsin-​Madison

Maurer Letizia |et|z|@m@urer @end|ng |rom ethz@ch
Thu Oct 15 08:50:24 CEST 2020


Dear all

We are glad to announce the following talk in the virtual ETH Young Data Science Researcher Seminar Zurich

"Learning from Small Data"  
by Ramya Korlakai Vinayak, University of Wisconsin-​Madison

Time: Friday, 16 October 2020, 15:00-​16:00
Place: Zoom at https://ethz.zoom.us/j/92367940258

Abstract: Many scientific domains such as social sciences and epidemiology study heterogeneous populations (varying demographics) with only a few (small) observations available at the level of individuals. Limited observations prohibit accurate estimation of parameters of interest for any given individual. In this small data regime, the key question is, how accurately can we estimate the distribution of parameters over the population? In this talk, we investigate this fundamental and practically relevant problem of learning from a heterogeneous population with small data in the Binomial observation setting. While the maximum likelihood estimator (MLE) is widely used for this problem, its optimality and sample complexity in the small data regime were not well understood. We prove that the MLE is optimal even in the small data regime, resolving this problem open since the 1960s. We then use these results to construct new, optimal estimators for learning the change in the parameters over the population.

Best wishes,

M. Azadkia, Y. Chen, M. Löffler, A. Taeb

Seminar website: https://math.ethz.ch/sfs/news-and-events/young-data-science.html


More information about the Statlist mailing list