activity
20172024
most citedWhat You See May Not Be What You Get: UCB Bandit Algorithms Robust to ε-Contamination

5 citations · 12 across the 5 of their papers we have counts for

collaborators
Showing cs.CYShow all

2 papers · 1 filter

cs.CY2018★ 5 cited

Debiasing representations by removing unwanted variation due to protected attributes

Amanda Bower, Laura Niss, Yuekai Sun +1

We propose a regression-based approach to removing implicit biases in representations. On tasks where the protected attribute is observed, the method is statistically more efficien…

cs.CY2017

Fair Pipelines

Amanda Bower, Sarah N. Kitchen, Laura Niss +3

This work facilitates ensuring fairness of machine learning in the real world by decoupling fairness considerations in compound decisions. In particular, this work studies how fair…