The Many Faces of Multiplicity in ML

There is a growing debate about the implications of multiplicity, conflicting behavior among a set of “good”' models, for algorithmic decision-making. On one hand, there are concerns over unfair treatment due to conflicting predictions and explanations, further exacerbated in the generative AI ecosystem. Yet, on the other hand, multiplicity also offers the potential to find less discriminatory and more interpretable models. In this tutorial, we aim to increase awareness of different perspectives on multiplicity and position them among broader discussions in the community. Specifically, the main goals of our tutorial are,

• Highlight the phenomenon of multiplicity in machine learning and call attention to its growing literature.
• Link multiplicity with uncertainty and churn, presenting a unified view of various measures of instability.
• Discuss the implications of multiplicity for fairness and explainability in algorithmic decision-making.
• Recognize exacerbated concerns and new forms of multiplicity in the age of generative AI.
• Engage the community on when and how to address multiplicity in various practical scenarios.
• Identify open questions and motivate future research directions on multiplicity.

Any feedback for our tutorial or want to be updated about future events? Please use the feedback form and join the mailing list, links above.

The tutorial is designed to be accessible to a multidisciplinary audience, targeted towards both academic researchers and industry practitioners. No technical prerequisite knowledge is required.