On the number of modes of Gaussian kernel density estimators

Autor: Geshkovski, Borjan, Rigollet, Philippe, Sun, Yihang
Rok vydání: 2024
Předmět:
Druh dokumentu: Working Paper
Popis: We consider the Gaussian kernel density estimator with bandwidth $\beta^{-\frac12}$ of $n$ iid Gaussian samples. Using the Kac-Rice formula and an Edgeworth expansion, we prove that the expected number of modes on the real line scales as $\Theta(\sqrt{\beta\log\beta})$ as $\beta,n\to\infty$ provided $n^c\lesssim \beta\lesssim n^{2-c}$ for some constant $c>0$. An impetus behind this investigation is to determine the number of clusters to which Transformers are drawn in a metastable state.
Databáze: arXiv