A local stochastic Lipschitz condition with application to Lasso for high dimensional generalized linear models

Details A local stochastic Lipschitz condition with application to Lasso for high dimensional generalized linear models A local stochastic Lipschitz condition with application to Lasso for high dimensional generalized linear models

2010-09-06

arxiv.org/abs/1009.1052v1

Mathematics

Statistics Theory

Scientific paper

For regularized estimation, the upper tail behavior of the random Lipschitz coefficient associated with empirical loss functions is known to play an important role in the error bound of Lasso for high dimensional generalized linear models. The upper tail behavior is known for linear models but much less so for nonlinear models. We establish exponential type inequalities for the upper tail of the coefficient and illustrate an application of the results to Lasso likelihood estimation for high dimensional generalized linear models.

Affiliated with

Also associated with

No associations

Rating

A local stochastic Lipschitz condition with application to Lasso for high dimensional generalized linear models does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A local stochastic Lipschitz condition with application to Lasso for high dimensional generalized linear models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A local stochastic Lipschitz condition with application to Lasso for high dimensional generalized linear models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-298082