Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models

neural information processing systems, pp. 8069-8079, 2019.

Cited by: 18|Bibtex|Views35|Links
EI
Keywords:
sample complexitylogistic regressionweight vectormarkov graphconvex program

Abstract:

We characterize the effectiveness of a classical algorithm for recovering the Markov graph of a general discrete pairwise graphical model from i.i.d. samples. The algorithm is (appropriately regularized) maximum conditional log-likelihood, which involves solving a convex program for each node; for Ising models this is 1-constrained logist...More

Code:

Data:

Your rating :
0

 

Tags
Comments