This paper investigates the asymptotic distribution of the maximum-likelihood estimate (MLE) in multinomial logistic models in the high-dimensional regime where dimension and sample size are of the same order.

Lijun Zhang is the corresponding author.

To mitigate the negative effect of data heterogeneity (non-IIDness), two common approaches are clustering and personalization.

To address these problems, in this paper we explore a simple yet effective decompositional approach towards both evaluation and improvement of text-to-image alignment.