Optimal Activation Functions for the Random Features Regression Model

Jianxin Wang; José Bento

ICLR 2023poster3 citations

Optimal Activation Functions for the Random Features Regression Model

Abstract

The asymptotic mean squared test error and sensitivity of the Random Features Regression model (RFR) have been recently studied. We build on this work and identify in closed-form the family of Activation Functions (AFs) that minimize a combination of the test error and sensitivity of the RFR under different notions of functional parsimony. We find scenarios under which the optimal AFs are linear, saturated linear functions, or expressible in terms of Hermite polynomials. Finally, we show how using optimal AFs impacts well established properties of the RFR model, such as its double descent curve, and the dependency of its optimal regularization parameter on the observation noise level.

Random Features Regression ModelLearning theory for neural networksFunctional analysis and variational calculus

BibTeX

@inproceedings{
wang2023optimal,
title={Optimal Activation Functions for the Random Features Regression Model},
author={Jianxin Wang and Jos{\'e} Bento},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=ltWade-cpK}
}