[YPNG] YPNG 15 April 2016

[Sekhar Tatikonda]

Hi Everyone,

This coming Friday Yu Lu will talk about:

Exact Exponent in Optimal Rates for Crowdsourcing
Crowdsourcing has become a popular tool for labeling large datasets. This
paper studies the optimal error rate for aggregating crowdsourced labels
provided by a collection of amateur workers. Under the Dawid-Skene
probabilistic model, we establish matching upper and lower bounds with an
exact exponent $mI(\pi)$, where $m$ is the number of workers and $I(\pi)$
is the average Chernoff information that characterizes the workers'
collective ability. Such an exact characterization of the error exponent
allows us to state a precise sample size requirement
$m>\frac{1}{I(\pi)}\log\frac{1}{\epsilon}$ in order to achieve an
$\epsilon$ misclassification error. In addition, our results imply the
optimality of various forms of EM algorithms given accurate initializers of
the model parameters.  This is a joint work with Chao Gao and Dengyong Zhou
from Microsoft Research.

See you Friday at 11am in the Stat's classroom.

Regards,
sekhar
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.yale.edu/pipermail/ypng/attachments/20160410/0e5cb855/attachment.html