000205082 001__ 205082
000205082 005__ 20180317093628.0
000205082 037__ $$aCONF
000205082 245__ $$aConsistency of $\ell_1$-Regularized Maximum-Likelihood for Compressive Poisson Regression
000205082 269__ $$a2015
000205082 260__ $$c2015
000205082 336__ $$aConference Papers
000205082 520__ $$aWe consider Poisson regression with the canonical link function. This regression model is widely used in regression analysis involving count data; one important application in electrical engineering is transmission tomography. In this paper, we establish the variable selection consistency and estimation consistency of the $\ell_1$-regularized maximum-likelihood estimator in this regression model, and characterize the asymptotic sample complexity that ensures consistency even under the compressive sensing setting (or the $n \ll p$ setting in high-dimensional statistics).
000205082 700__ $$0247574$$aLi, Yen-Huan$$g221971
000205082 700__ $$0243957$$aCevher, Volkan$$g199128
000205082 7112_ $$a40th IEEE Int. Conf. Acoustics, Speech and Signal Processing$$cBrisbane, Australia$$dApril 19-24, 2015
000205082 8564_ $$s261402$$uhttps://infoscience.epfl.ch/record/205082/files/poisson_consistency.pdf$$yPreprint$$zPreprint
000205082 909CO $$ooai:infoscience.tind.io:205082$$pSTI$$pconf
000205082 909C0 $$0252306$$pLIONS$$xU12179
000205082 917Z8 $$x221971
000205082 917Z8 $$x221971
000205082 937__ $$aEPFL-CONF-205082
000205082 973__ $$aEPFL$$rREVIEWED$$sACCEPTED
000205082 980__ $$aCONF