As algorithms increasingly inform and influence decisions made about individuals, it becomes increasingly important to address concerns that these algorithms might be discriminatory. Multicalibration guarantees accurate (calibrated) predictions for every subpopulation that can be identified within a rich class of computations. It strives to protect against data analysis that inadvertently or maliciously introduces biases that are not borne out in the training data. Multicalibration may also help address other forms of oppression, that may require affirmative action or social engineering. In this talk, we will discuss how this notion, recently introduced within the research area of Algorithmic Fairness, has found a surprising set of practical and theoretical implications. We will discuss multicalibration and touch upon some of its unexpected consequences, including:
- Practical methods for learning in a heterogeneous population, employed in the field to predict COVID-19 complications at a very early stage of the pandemic.
- A computational perspective on the meaning of individual probabilities through the new notion of outcome indistinguishability.
- A rigorous new paradigm for loss minimization in machine learning, through the notion of omnipredictors, that simultaneously applies to a wide class of loss-functions, allowing the specific loss function to be ignored at the time of learning.
- A method for adapting a statistical study on one probability distribution to another, which is blind to the target distribution at the time of inference and is competitive with wide-spread methods based on propensity scoring. Based on a sequence of works joint with (subsets of) Cynthia Dwork, Shafi Goldwasser, Parikshit Gopalan, Úrsula Hébert-Johnson, Adam Kalai, Christoph Kern, Michael P. Kim, Frauke Kreuter, Guy N. Rothblum, Vatsal Sharan, Udi Wieder, and Gal Yona.
Speaker Biography
Omer Reingold is the Rajeev Motwani professor of computer science at Stanford University and the director of the Simons Collaboration on the Theory of Algorithmic Fairness. Past positions include the Weizmann Institute of Science, Microsoft Research, the Institute for Advanced Study in Princeton, NJ, AT&T Labs and Samsung Research America. His research is in the foundations of computer science and most notably in computational complexity, cryptography and the societal impact of computation. He is an ACM Fellow and a Simons Investigator. Among his distinctions are the 2005 Grace Murray Hopper Award and the 2009 Gödel Prize.