Can I read Using Pareto Simulated Annealing to Address Algorithmic Bias in Machine Learning on EtoBox?

Using Pareto Simulated Annealing to Address Algorithmic Bias in Machine Learning by Blanzeisky, William; Cunningham, Pádraig is a scholarly article available to read on EtoBox.

What is Using Pareto Simulated Annealing to Address Algorithmic Bias in Machine Learning about?

Algorithmic Bias can be due to bias in the training data or issues with the algorithm itself. These algorithmic issues typically relate to problems with model capacity and regularisation. This underestimation bias may arise because the model has been optimised for good generalisation accuracy without any explicit consideration of bias or fairness. In a sense, we should not be surprised that a model might be biased when it hasn't been "asked" not to be. In this paper, we consider including bias (underestimation) as an additional criterion in model training. We present a multi-objective optimisation strategy using Pareto Simulated Annealing that optimise for both balanced accuracy and underestimation. We demonstrate the effectiveness of this strategy on one synthetic and two real-world datasets.

Author

Blanzeisky, William; Cunningham, Pádraig

Published

2021

Language

EN