Home /  Workshop /  Schedules /  Multiplicity in Machine Learning

Multiplicity in Machine Learning

Randomization, Neutrality, and Fairness October 23, 2023 - October 27, 2023

October 24, 2023 (11:00 AM PDT - 12:00 PM PDT)
Speaker(s): Flavio Calmon (Harvard University)
Location: SLMath: Eisenbud Auditorium, Online/Virtual
Primary Mathematics Subject Classification No Primary AMS MSC
Secondary Mathematics Subject Classification No Secondary AMS MSC
Video
No Video Uploaded
Abstract

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.

Supplements No Notes/Supplements Uploaded
Video/Audio Files
No Video Files Uploaded