We consider the problem of fitting a probability density function when it is constrained to have a given number of modal intervals. We propose a dynamic programming approach to solving this problem numerically. When this number is not known, we provide several data-driven ways for selecting it. We perform some numerical experiments to illustrate our methodology.
@article{arxiv.2207.11121,
title = {Fitting a Multi-modal Density by Dynamic Programming},
author = {Ery Arias-Castro and He Jiang},
journal= {arXiv preprint arXiv:2207.11121},
year = {2022}
}