Fréchet regression has emerged as a promising approach for regression analysis involving non-Euclidean response variables.

In this work, we investigate an alternative setting for tuning regularization parameters, namely data-driven algorithm design, following the previous line of work by Balcan et al. [

Our framework applies to a wide range of SMF-type problems for multi-class classification with auxiliary features.

However, sampling is not the only source of uncertainty. In practice, distributions change between locations and across time.

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.