A Power Transform

2025/02/15 by Jonathan T. Barron, J. T. Barron, Barron, Jonathan T. · 1 voice
Computer Science · Mathematics · #Advanced Statistical Methods and Models #Advanced Statistical Modeling Techniques #Computational Physics and Python Applications #cs.LG #math.ST #stat.ML

paper · pdf · doi:10.48550/arxiv.2502.10647

openalex publication_date 2025/02/15 · openalex created_date 2025/02/19 · openalex updated_date 2026/07/28

Abstract

Power transforms, such as the Box-Cox transform and Tukey's ladder of powers, are a fundamental tool in mathematics and statistics. These transforms are primarily used for normalizing and standardizing datasets, effectively by raising values to a power. In this work I present a novel power transform, and I show that it serves as a unifying framework for wide family of loss functions, kernel functions, probability distributions, bump functions, and neural network activation functions.

Discussions

• There's more good stuff in the paper: arxiv.org/abs/2502.10647. This paper is maybe a little strange because I "wrote it for the LLMs" --- it's a deep dive into a low level model component that would [bsky, 9 points, 2 comments]

Related

• Power Transform Revisited: Numerically Stable, and Federated
• Notes on Correspondence Analysis of Power Transformed Data Sets
• Advancements in Signal Processing and Control Systems Using Z and L-Transforms
• First Power Linear Unit with Sign
• Fitting heavy tailed distributions: the poweRlaw package