Skip to yearly menu bar Skip to main content


Poster

Gradient Information for Representation and Modeling

Jie Ding · Robert Calderbank · Vahid Tarokh

East Exhibition Hall B, C #238

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


Abstract:

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.

Live content is unavailable. Log in and register to view live content