Bregman distance to L1 regularized logistic regression

In this work we investigate the relationship between Bregman distances and regularized Logistic Regression model. We present a detailed study of Bregman Distance minimization, a family of generalized entropy measures associated with convex functions. We convert the L1-regularized logistic regression into this more general framework and propose a primal-dual method based algorithm for learning the parameters. We pose L1regularized logistic regression into Bregman distance minimization and then apply nonlinear constrained optimization techniques to estimate the parameters of the logistic model.

• Type: Conference
• Year: 2008
• Where: ICPR
• Authors: Mithun Das Gupta, Thomas S. Huang
• Keywords: Bregman Distance Minimization, Computer Vision, ICPR 2008, L1-regularized Logistic Regression, Regularized Logistic Regression