7 papers
Perceptions of the Fairness Impacts of Multiplicity in Machine Learning
Anna P. Meyer, Yea-Seul Kim, Aws Albarghouthi +1
Machine learning (ML) is increasingly used in high-stakes settings, yet multiplicity - the existence of multiple good models - means that some predictions are essentially arbitrary…
Verified Training for Counterfactual Explanation Robustness under Data Shift
Anna P. Meyer, Yuhao Zhang, Aws Albarghouthi +1
Counterfactual explanations (CEs) enhance the interpretability of machine learning models by describing what changes to an input are necessary to change its prediction to a desired…
On Minimizing the Impact of Dataset Shifts on Actionable Explanations
Anna P. Meyer, Dan Ley, Suraj Srinivas +1
The Right to Explanation is an important regulatory principle that allows individuals to request actionable explanations for algorithmic decisions. However, several technical chall…
The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions
Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
We introduce dataset multiplicity, a way to study how inaccuracies, uncertainty, and social bias in training datasets impact test-time predictions. The dataset multiplicity framewo…
A machine learning based algorithm selection method to solve the minimum cost flow problem
Philipp Herrmann, Anna Meyer, Stefan Ruzika +2
The minimum cost flow problem is one of the most studied network optimization problems and appears in numerous applications. Some efficient algorithms exist for this problem, which…
Certifying Data-Bias Robustness in Linear Regression
Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
Datasets typically contain inaccuracies due to human error and societal biases, and these inaccuracies can affect the outcomes of models trained on such datasets. We present a tech…
Certifying Robustness to Programmable Data Bias in Decision Trees
Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
Datasets can be biased due to societal inequities, human biases, under-representation of minorities, etc. Our goal is to certify that models produced by a learning algorithm are po…