10 papers
Law of Large Numbers: Accuracy as Statistical Measure for AI Compliance and Competition
Rabanus Derr, Alina Wernick, Robert C. Williamson
The machine learning community progresses (in part) by improving the "accuracy" of its systems. The EU AI Act explicitly refers to "accuracy" as part of its compliance measures for…
Comparing Corrupted Constrained Learning Problems
Laura Iacovissi, Rabanus Derr, Robert C. Williamson
A key result in statistics is the data processing inequality, originally proved by Blackwell (1951) and later refined by DeGroot (1962) in terms of statistical uncertainty. The lat…
Property Elicitation on Imprecise Probabilities
James Bailie, Rabanus Derr
Property elicitation studies which attributes of a probability distribution can be determined by minimizing a risk. We investigate a generalization of property elicitation to impre…
Three Types of Calibration with Properties and their Semantic and Formal Relationships
Rabanus Derr, Jessie Finocchiaro, Robert C. Williamson
Fueled by discussions around "trustworthiness" and algorithmic fairness, calibration of predictive systems has regained scholars attention. The vanilla definition and understanding…
The Value of Ambiguous Commitments in Multi-Follower Games
Natalie Collina, Rabanus Derr, Aaron Roth
We study games in which a leader makes a single commitment, and then multiple followers (each with a different utility function) respond. In particular, we study ambiguous commitme…
An Axiomatic Approach to Loss Aggregation and an Adapted Aggregating Algorithm
Armando J. Cabrera Pacheco, Rabanus Derr, Robert C. Williamson
Supervised learning has gone beyond the expected risk minimization framework. Central to most of these developments is the introduction of more general aggregation functions for lo…
Evaluation Metrics as Averaged Outcomes of Fair Gambles
Rabanus Derr, Robert C. Williamson
In the current practices of machine learning, the evaluation of forecasts has become a cornerstone of scientific progress. A multitude of evaluation metrics have been suggested and…
Systems of Precision: Coherent Probabilities on Pre-Dynkin-Systems and Coherent Previsions on Linear Subspaces
Rabanus Derr, Robert C. Williamson
In literature on imprecise probability little attention is paid to the fact that imprecise probabilities are precise on a set of events. We call these sets systems of precision. We…
Strictly Frequentist Imprecise Probability
Christian Fröhlich, Rabanus Derr, Robert C. Williamson
Strict frequentism defines probability as the limiting relative frequency in an infinite sequence. What if the limit does not exist? We present a broader theory, which is applicabl…
Fairness and Randomness in Machine Learning: Statistical Independence and Relativization
Rabanus Derr, Robert C. Williamson
Fair Machine Learning endeavors to prevent unfairness arising in the context of machine learning applications embedded in society. Despite the variety of definitions of fairness an…