Multiplicity in Machine Learning
Randomization, Neutrality, and Fairness October 23, 2023 - October 27, 2023
Location: SLMath: Eisenbud Auditorium, Online/Virtual
Primary Mathematics Subject Classification
No Primary AMS MSC
Secondary Mathematics Subject Classification
No Secondary AMS MSC
This talk reviews the concept of predictive multiplicity in machine learning. Predictive multiplicity arises when different classifiers achieve similar average performance for a specific learning task yet produce conflicting predictions for individual samples. We discuss a metric called “Rashomon Capacity” for quantifying predictive multiplicity in multi-class classification. We also present recent findings on the multiplicity cost of differentially private training methods and group fairness interventions in machine learning.
This talk is based on work published at ICML'20, NeurIPS'22, ACM FAccT'23, and NeurIPS'23.