38 citations · 64 across the 5 of their papers we have counts for
7 papers
On The Impact of Machine Learning Randomness on Group Fairness
Prakhar Ganesh, Hongyan Chang, Martin Strobel +1
Statistical measures for group fairness in machine learning reflect the gap in performance of algorithms across different groups. These measures, however, exhibit a high variance b…
Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities
Xudong Shen, Hannah Brown, Jiashu Tao +5
There is increasing attention being given to how to regulate AI systems. As governing bodies grapple with what values to encapsulate into regulation, we consider the technical half…
Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play
Jeremiah Zhe Liu, Krishnamurthy Dj Dvijotham, Jihyeon Lee +4
Standard empirical risk minimization (ERM) training can produce deep neural network (DNN) models that are accurate on average but under-perform in under-represented population subg…
Data Privacy and Trustworthy Machine Learning
Martin Strobel, Reza Shokri
The privacy risks of machine learning models is a major concern when training them on sensitive and personal data. We discuss the tradeoffs between data privacy and the remaining g…
High Dimensional Model Explanations: an Axiomatic Approach
Neel Patel, Martin Strobel, Yair Zick
Complex black-box machine learning models are regularly used in critical decision-making domains. This has given rise to several calls for algorithmic explainability. Many explanat…
On the Privacy Risks of Model Explanations
Reza Shokri, Martin Strobel, Yair Zick
Privacy and transparency are two key foundations of trustworthy machine learning. Model explanations offer insights into a model's decisions on input data, whereas privacy is prima…
Axiomatic Characterization of Data-Driven Influence Measures for Classification
Jakub Sliwinski, Martin Strobel, Yair Zick
We study the following problem: given a labeled dataset and a specific datapoint x, how did the i-th feature influence the classification for x? We identify a family of numerical i…