A Similarity Measure Between Functions with Applications to Statistical Learning and Optimization
Machine Learning
2025-01-15 v1 Optimization and Control
Machine Learning
Abstract
In this note, we present a novel measure of similarity between two functions. It quantifies how the sub-optimality gaps of two functions convert to each other, and unifies several existing notions of functional similarity. We show that it has convenient operation rules, and illustrate its use in empirical risk minimization and non-stationary online optimization.
Cite
@article{arxiv.2501.08317,
title = {A Similarity Measure Between Functions with Applications to Statistical Learning and Optimization},
author = {Chengpiao Huang and Kaizheng Wang},
journal= {arXiv preprint arXiv:2501.08317},
year = {2025}
}
Comments
9 pages