Spectral risk-based learning using unbounded losses
Machine Learning
2021-05-12 v1 Machine Learning
Abstract
In this work, we consider the setting of learning problems under a wide class of spectral risk (or "L-risk") functions, where a Lipschitz-continuous spectral density is used to flexibly assign weight to extreme loss values. We obtain excess risk guarantees for a derivative-free learning procedure under unbounded heavy-tailed loss distributions, and propose a computationally efficient implementation which empirically outperforms traditional risk minimizers in terms of balancing spectral risk and misclassification error.
Cite
@article{arxiv.2105.04816,
title = {Spectral risk-based learning using unbounded losses},
author = {Matthew J. Holland and El Mehdi Haress},
journal= {arXiv preprint arXiv:2105.04816},
year = {2021}
}