2000 character limit reached
The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression
Published 25 Apr 2018 in stat.ME and stat.ML | (1804.09753v1)
Abstract: This paper rigorously establishes that the existence of the maximum likelihood estimate (MLE) in high-dimensional logistic regression models with Gaussian covariates undergoes a sharp `phase transition'. We introduce an explicit boundary curve , parameterized by two scalars measuring the overall magnitude of the unknown sequence of regression coefficients, with the following property: in the limit of large sample sizes and number of features proportioned in such a way that , we show that if the problem is sufficiently high dimensional in the sense that , then the MLE does not exist with probability one. Conversely, if , the MLE asymptotically exists with probability one.
Paper Prompts
Sign up for free to create and run prompts on this paper.