[Ml-stat-talks] Fwd: Tomorrow: CSML Seminar Series | David Dunson (Duke University) - "Scalable Bayes" | Tuesday, November 4, 2015 at 4:30pm

Barbara Engelhardt bee at CS.Princeton.EDU
Mon Nov 3 13:00:37 EST 2014


---------- Forwarded message ----------
From: Storey, John D. <jstorey at princeton.edu>
Date: Mon, Nov 3, 2014 at 12:42 PM
Subject: Tomorrow: CSML Seminar Series | David Dunson (Duke University) -
"Scalable Bayes" | Tuesday, November 4, 2015 at 4:30pm
To: CSML-seminars at princeton.edu


 Hi everyone,

 David Dunson is speaking tomorrow at the first ever Center for Statistics
and Machine Learning seminar.  Details are below. I hope to see you there!

 John

 *David Dunson, Duke University*
*CS 105 on November 4 at 4:30PM*
Title: Scalable Bayes
 Abstract:  Bayesian methods have great promise in big data sets, but this
promise has not been fully realized due to the lack of scalable and robust
algorithms.  Usual sampling approaches bog down as the size of the data and
number of parameters increase.  For massive data sets, it has become
routine to rely on penalized optimization approaches implemented on
distributed computing systems.  However, in scientific applications, it is
crucial to obtain a good characterization of uncertainty and not simply a
point estimate.  We propose several fundamentally new approaches for
scaling up, which we illustrate through large survey data sets,
neurosciences and genomics.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20141103/44fc34cb/attachment.html>


More information about the Ml-stat-talks mailing list