Reluctant generalized additive modeling

TL;DR

This paper introduces RGAM, a scalable multi-stage algorithm for fitting sparse generalized additive models that prefers linear features over non-linear ones, extending to various data types.

Contribution

The paper proposes RGAM, a novel scalable method for sparse GAMs that can be extended to binary, count, and survival data, improving modeling flexibility.

Findings

RGAM effectively fits sparse GAMs on real and simulated data.

It outperforms existing methods in scalability and flexibility.

The approach aligns with the principle of preferring linear features when possible.

Abstract

Sparse generalized additive models (GAMs) are an extension of sparse generalized linear models which allow a model's prediction to vary non-linearly with an input variable. This enables the data analyst build more accurate models, especially when the linearity assumption is known to be a poor approximation of reality. Motivated by reluctant interaction modeling (Yu et al. 2019), we propose a multi-stage algorithm, called $\textit{reluctant generalized additive modeling (RGAM)}$, that can fit sparse generalized additive models at scale. It is guided by the principle that, if all else is equal, one should prefer a linear feature over a non-linear feature. Unlike existing methods for sparse GAMs, RGAM can be extended easily to binary, count and survival data. We demonstrate the method's effectiveness on real and simulated examples.