pLSA for Sparse Arrays With Tsallis Pseudo-Additive Divergence: Noise Robustness and Algorithm

Tamir Hazan, Roee Hardoon, Amnon Shashua
2007 2007 IEEE 11th International Conference on Computer Vision  
We introduce the Tsallis divergence error measure in the context of pLSA matrix and tensor decompositions showing much improved performance in the presence of noise. The focus of our approach is on one hand to provide an optimization framework which extends (in the sense of a one parameter family) the Maximum Likelihood framework and on the other hand is theoretically guaranteed to provide robustness under clutter, noise and outliers in the measurement matrix under certain conditions.
more » ... nditions. Specifically, the conditions under which our approach excels is when the measurement array (co-occurrences) is sparse -which happens in the application domain of "bag of visual words".
doi:10.1109/iccv.2007.4409048 dblp:conf/iccv/HazanHS07 fatcat:tsnfvmgarrfd3nbgki76trl5lq