Considerations Across Three Cultures: Parametric Regressions, Interpretable Algorithms, and Complex Algorithms

no code implementations • 14 Apr 2021 • Ani Eloyan, Sherri Rose

We consider an extension of Leo Breiman's thesis from "Statistical Modeling: The Two Cultures" to include a bifurcation of algorithmic modeling, focusing on parametric regressions, interpretable algorithms, and complex (possibly explainable) algorithms.

Principal manifold estimation via model complexity selection

1 code implementation • 17 Nov 2017 • Kun Meng, Ani Eloyan

We propose a framework of principal manifolds to model high-dimensional data.

Methodology