BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Efficient Profile Maximum Likelihood for Universal 
 Symmetric Property Estimation
DTSTART:20181213T161500
DTEND:20181213T173000
DTSTAMP:20260407T001428Z
UID:ef2fc55a7d5af76df1b01fe097b1e09c6e8d2b25141f6f9a2111eafa
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Moses Charikar - Stanford University\nVideo of his talk\n\
 nAbstract:\nSymmetric properties of distributions arise in multiple settin
 gs. For each of these\, separate estimators and analysis techniques have b
 een developed. Recently\, Orlitsky et al showed that a single estimator th
 at maximizes profile maximum likelihood (PML) is sample competitive for al
 l symmetric properties. Further\, they showed that even a 2^{n^{1-delta}}-
 approximate maximizer of the PML objective can serve as such a universal p
 lug-in estimator. (Here n is the size of the sample). Unfortunately\, no p
 olynomial time computable PML estimator with such an approximation guarant
 ee was known. We provide the first such estimator and show how to compute 
 it in time nearly linear in n.\n\nJoint work with Kiran Shiragur and Aaron
  Sidford.\n\nBio:\nMoses Charikar is a professor of Computer Science at St
 anford University. He obtained his PhD from Stanford in 2000\, spent a yea
 r in the research group at Google\, and was on the faculty at Princeton fr
 om 2001-2015. He is broadly interested in approximation algorithms (especi
 ally the power of mathematical programming approaches)\, metric embeddings
 \, algorithmic techniques for big data\, efficient algorithms for computat
 ional problems in high-dimensional statistics and optimization problems in
  machine learning. He won the best paper award at FOCS 2003 for his work o
 n the impossibility of dimension reduction\, the best paper award at COLT 
 2017 and the 10 year best paper award at VLDB 2017. He was jointly awarded
  the 2012 Paris Kanellakis Theory and Practice Award for his work on local
 ity sensitive hashing inspired by random hyperplane rounding\, and was nam
 ed a Simons Investigator in theoretical computer science in 2014.\n\nMore 
 information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR