Robust Risk Minimization for Statistical Learning
Machine Learning
2020-02-10 v2 Machine Learning
Signal Processing
Abstract
We consider a general statistical learning problem where an unknown fraction of the training data is corrupted. We develop a robust learning method that only requires specifying an upper bound on the corrupted data fraction. The method minimizes a risk function defined by a non-parametric distribution with unknown probability weights. We derive and analyse the optimal weights and show how they provide robustness against corrupted data. Furthermore, we give a computationally efficient coordinate descent algorithm to solve the risk minimization problem. We demonstrate the wide range applicability of the method, including regression, classification, unsupervised learning and classic parameter estimation, with state-of-the-art performance.
Cite
@article{arxiv.1910.01544,
title = {Robust Risk Minimization for Statistical Learning},
author = {Muhammad Osama and Dave Zachariah and Peter Stoica},
journal= {arXiv preprint arXiv:1910.01544},
year = {2020}
}