\documentclass[11pt]{article}
\setlength{\oddsidemargin}{0.0truein}
\setlength{\evensidemargin}{0.0truein}
\setlength{\textwidth}{6.5truein}
\setlength{\topmargin}{0.0truein}
\setlength{\textheight}{9.0truein} \setlength{\headsep}{0.0truein}
\setlength{\headheight}{0.0truein} \setlength{\topskip}{10.0pt}
\setlength{\parskip}{5mm}
\usepackage{url}
\begin{document}

\begin{center}
  \textbf{\textsc{STANFORD UNIVERSITY}}\\[5pt]
  \textbf{\textsc{DEPARTMENT OF STATISTICS}}\\[5pt]
  \Large{\textbf\textsc{{DEPARTMENTAL SEMINAR}}}
\end{center}

\begin{center}
  4:15 p.m., Tuesday, February 28, 2006\\
  Sequoia Hall Room 200\\
  (Cookies at 3:45 in 1st Floor Lounge)
\end{center}

\begin{center}
  \textsl{Ben Tasker}\\
Electrical Engineering and Computer Science Department \\
University of California at Berkeley\\
\end{center}

\begin{center}
  \textbf{Computationally Efficient Estimation of \\
Structured Prediction Models}
\end{center}


\noindent
Structured prediction problems are classification or regression 
problems in which the output variables are mutually dependent or 
constrained.  These dependencies and constraints may reflect 
sequential, spatial or combinatorial structure in the problem 
domain, and capturing these interactions is often as important 
for the purposes of prediction as capturing input-output 
dependencies. 

\noindent
Graphical models are used to represent such problem structure 
across many fields, including computational biology, vision and 
linguistics.

\noindent
Typical models are comprised of hundreds of thousands of variables 
and parameters.  In general, the standard (likelihood-based) 
estimation of such models is intractable because of the exponential 
explosion of the number of possible joint outcomes. 

\noindent
By drawing on ideas from convex and combinatorial optimization, 
I will show an alternative estimation method that is tractable 
for several important classes of models for which standard 
methods are not.  I will demonstrate practical applications of 
these models for problems in object recognition, protein folding, 
and machine translation. 
 

 

\noindent
Short Biography: 

\noindent
Ben Taskar received his bachelor's degree with distinction in 
Computer Science from Stanford University.  He later returned to 
Stanford for his master and doctoral degrees in Computer Science. 
He is currently a postdoctoral fellow at the Electrical Engineering 
and Computer Science Department at the University of California at 
Berkeley. His research interests include machine learning, 
graphical models, large-scale and distributed convex optimization, 
and applications in computer vision, computational biology and 
natural language processing. His work on structured prediction 
models has received best student paper award at the Neural 
Information Processing Systems (NIPS) conference and best paper 
award at the Empirical Methods in Natural Language Processing 
(EMNLP) conference, and his doctoral dissertation was selected 
runner-up for the Arthur Samuel Best Thesis Award.

\end{document}