[Colloquium] TTIC Talk: Miroslav Dudik

[Julia MacGlashan]

*REMINDER*

When:             *Thursday, Jan 28 @ 11:00am*

Where:           * TTI-C Conference Room #526*, 6045 S Kenwood Ave


Who:               *Miroslav Dudik*, CMU


Title:          *      **Maximum entropy and applications in natural and
social sciences*



 The maximum entropy approach (maxent), equivalent to maximum likelihood, is
a widely used density-estimation technique. However, when trained on small
datasets, maxent is likely to overfit, and when trained over large sample
spaces, naive implementations of maxent are intractable. To prevent
overfitting, we propose a relaxed version of maxent, which turns out to be
equivalent to L1-regularized log likelihood. We prove strong statistical
guarantees for L1-regularized maxent, and show how it can be generalized to
the problem of estimation in the presence of sample-selection bias. To
address computational challenges, we propose an approach based on sampling
and coordinate descent.

I discuss two applications of maxent: statistical modeling of distributions
of biological species and game-theoretic modeling of human negotiation,
focusing mainly on the former. In species distribution modeling, statistical
properties of regularized maxent are key in obtaining state-of-the-art
performance on small data sets. In game-theoretic modeling, the coordinate
descent algorithm and sampling allow our approach to solve negotiation
scenarios an order of magnitude larger than previous techniques.

Based on joint work with Rob Schapire, Steven Phillips, Geoff Gordon and
others.

Host:              Nati Srebro, nati at ttic.edu*
*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20100127/3feb3037/attachment.htm