Timezone: »

 
Poster
Gradient Information for Representation and Modeling
Jie Ding · Robert Calderbank · Vahid Tarokh

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #238
in Theory -- Information Theory »

Motivated by Fisher divergence, in this paper we present a new set of information quantities which we refer to as gradient information. These measures serve as surrogates for classical information measures such as those based on logarithmic loss, Kullback-Leibler divergence, directed Shannon information, etc. in many data-processing scenarios of interest, and often provide significant computational advantage, improved stability and robustness. As an example, we apply these measures to the Chow-Liu tree algorithm, and demonstrate remarkable performance and significant computational reduction using both synthetic and real data.

Keywords: Information Theory · Representation Learning · Algorithms · Algorithms -> Clustering; Theory
[ Paper]  [ Slides] 

Author Information

Jie Ding (University of Minnesota)
Robert Calderbank (Duke University)
Vahid Tarokh (Duke University)

More from the Same Authors