Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Aggregating Concepts of Fairness and Accuracy in Prediction Algorithms
David Kinney
An algorithm that outputs predictions about the state of the world will almost always be designed with the implicit or explicit goal of outputting accurate predictions (i.e., predi…
cs.LG2023
Loop Polarity Analysis to Avoid Underspecification in Deep Learning
Donald Martin, David Kinney
Deep learning is a powerful set of techniques for detecting complex patterns in data. However, when the causal structure of that process is underspecified, deep learning models can…