Search Mailing List Archives


Limit search to: Subject & Body Subject Author
Sort by: Reverse Sort
Limit to: All This Week Last Week This Month Last Month
Select Date Range     through    

[theory-seminar] Theory Lunch 10/03 - Kiran Shiragur

Neha Gupta nehgupta at stanford.edu
Wed Oct 2 10:00:50 PDT 2019


Hi everyone,

This Thursday at theory lunch, Kiran will tell us about recent developments on the Profile Maximum Likelihood problem (title and abstract below). As usual, please join us from noon - 1pm in Gates 463A.

-----------------------------

Title:  Recent developments on the Profile Maximum Likelihood problem

Abstract:  Symmetric properties of distributions arise in multiple settings. For each of these, separate estimators and analysis techniques have been developed. Recently, Orlitsky et al showed that a single estimator that maximizes profile maximum likelihood (PML) is sample competitive for all symmetric properties. Further, they showed that even a 2^{n^{1-delta}}-approximate maximizer of the PML objective can serve as such a universal plug-in estimator. (Here n is the size of the sample). Unfortunately, no polynomial time computable PML estimator with such an approximation guarantee was known. In this talk, I will describe our contribution and other recent developments made on the problem.

This is based on joint works with Moses Charikar and Aaron Sidford.

-------------------------------

Thanks,
Neha

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.stanford.edu/pipermail/theory-seminar/attachments/20191002/b4cb38d3/attachment-0003.html>


More information about the theory-seminar mailing list