TY - GEN
T1 - Information theoretic validity of penalized likelihood
AU - Chatterjee, Sabyasachi
AU - Barron, Andrew
PY - 2014
Y1 - 2014
N2 - Building upon past work, which developed information theoretic notions of when a penalized likelihood procedure can be interpreted as codelengths arising from a two stage code and when the statistical risk of the procedure has a redundancy risk bound, we present new results and risk bounds showing that the l1 penalty in Gaussian Graphical Models fits the above story. We also show how the traditional l0 penalty times plus lower order terms which stay bounded on the whole parameter space has a conditional two stage description length interpretation.
AB - Building upon past work, which developed information theoretic notions of when a penalized likelihood procedure can be interpreted as codelengths arising from a two stage code and when the statistical risk of the procedure has a redundancy risk bound, we present new results and risk bounds showing that the l1 penalty in Gaussian Graphical Models fits the above story. We also show how the traditional l0 penalty times plus lower order terms which stay bounded on the whole parameter space has a conditional two stage description length interpretation.
UR - https://www.scopus.com/pages/publications/84906544671
UR - https://www.scopus.com/pages/publications/84906544671#tab=citedBy
U2 - 10.1109/ISIT.2014.6875390
DO - 10.1109/ISIT.2014.6875390
M3 - Conference contribution
AN - SCOPUS:84906544671
SN - 9781479951864
SN - 9781479951864
T3 - IEEE International Symposium on Information Theory - Proceedings
SP - 3027
EP - 3031
BT - 2014 IEEE International Symposium on Information Theory, ISIT 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE International Symposium on Information Theory, ISIT 2014
Y2 - 29 June 2014 through 4 July 2014
ER -