[Ml-stat-talks] matt taddy: monday november 11 at 1:30pm

David Blei blei at CS.Princeton.EDU
Tue Nov 5 22:11:26 EST 2013


hi carlos

do you mean jonathan chang?  are you at facebook?

your son has the same writing style as my daughter.  it's the new school.

best
dave


On Tue, Nov 5, 2013 at 10:03 PM, Carlos Diuk <carlosdiuk at gmail.com> wrote:
> Hhhhhhhhghjh un gym MOl O o pjo t FrT sa
>
>
> On Nov 5, 2013 6:57 PM, "David Blei" <blei at cs.princeton.edu> wrote:
>>
>> ml-stat-talks
>>
>> mark your calendars for next monday november 11 at 1:30pm.  matt taddy
>> from the university of chicago will discuss inverse regression,
>> including his latest JASA discussion paper "multinomial inverse
>> regression for text analysis".  matt has deep intuitions, interesting
>> results, and a fresh perspective on analyzing massive discrete data
>> sets.
>>
>> the details are below my signature.
>>
>> best
>> dave
>>
>> ---
>>
>> Inverse Regression for Analysis of Big Count Data
>> Matthew Taddy
>> University of Chicago
>>
>> Monday, November 11
>> 1:30PM
>> Computer Science, Room 301
>>
>> Much of the data we encounter occur as counts in a massive number of
>> categories: think of word usage in text mining, or domain visits in
>> web analytics. This data is accompanied by a smaller set of attributes
>> -- associated with, say, an author or IP address -- and we want to be
>> able to build a model that will be useful when some of these
>> attributes are unobserved.  This talk will discuss multinomial inverse
>> regression as a strategy for projecting from high-dimensional counts
>> onto such a set of attributes.  We'll consider the computational and
>> statistical reasons one would want to do this, and consider a series
>> of examples on how the techniques can work (or not work) in both
>> inference and prediction.
>> _______________________________________________
>> Ml-stat-talks mailing list
>> Ml-stat-talks at lists.cs.princeton.edu
>> https://lists.cs.princeton.edu/mailman/listinfo/ml-stat-talks


More information about the Ml-stat-talks mailing list