Gradient Information for Representation and Modeling
| 
94 | 
107 | 
0
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.
还没有评论，说两句吧！
热门资源
Deep Cross-media ...
Cross-media retrieval is a research hotspot in ...
Regularizing RNNs...
Recently, caption generation with an encoder-de...
Learning Expressi...
Facial expression is temporally dynamic event w...
Attributed Graph ...
Graph clustering is a fundamental task which di...
Compact MDDs for ...
Pseudo-Boolean (PB) constraints are usually en...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com
资源分类
