Sequential Linearithmic Time Optimal Unimodal Fitting When Minimizing Univariate Linear Losses
Machine Learning
2023-04-06 v1 Data Structures and Algorithms
Optimization and Control
Machine Learning
Abstract
This paper focuses on optimal unimodal transformation of the score outputs of a univariate learning model under linear loss functions. We demonstrate that the optimal mapping between score values and the target region is a rectangular function. To produce this optimal rectangular fit for the observed samples, we propose a sequential approach that can its estimation with each incoming new sample. Our approach has logarithmic time complexity per iteration and is optimally efficient.
Cite
@article{arxiv.2304.02141,
title = {Sequential Linearithmic Time Optimal Unimodal Fitting When Minimizing Univariate Linear Losses},
author = {Kaan Gokcesu and Hakan Gokcesu},
journal= {arXiv preprint arXiv:2304.02141},
year = {2023}
}
Comments
this work draws from arXiv:2108.08780