Mitigating multiple descents: A model-agnostic framework for risk monotonization. (arXiv:2205.12937v1 [math.ST])

Recent empirical and theoretical analyses of several commonly used prediction
procedures reveal a peculiar risk behavior in high dimensions, referred to as
double/multiple descent, in which the asymptotic risk is a non-monotonic
function of the limiting aspect ratio of the number of features or parameters
to the sample size. To mitigate this undesirable behavior, we develop a general
framework for risk monotonization based on cross-validation that takes as input
a generic prediction procedure and returns a modified procedure whose
out-of-sample …

arxiv framework math model-agnostic risk