[Theory] UC Theory Seminar: a reminder

[Alexander Razborov]

Departments of Mathematics & Computer Science
Combinatorics & Theory Seminar

Tuesday, May 3, 3:30pm
Location Kent 107

Omer Reingold (Stanford)

TITLE: Algorithmic Fairness, Loss Minimization and Outcome 
Indistinguishability

ABSTRACT: Training a predictor to minimize a loss function fixed in 
advance is the dominant paradigm in machine learning. However, loss 
minimization by itself might fail to satisfy properties that come 
naturally in the context of algorithmic fairness. To remedy this, 
multi-group fairness notions such as multi calibration have been 
proposed, which require the predictor to share certain statistical 
properties of the ground truth, even when conditioned on a rich family 
of subgroups. These notions could be understood from the perspective of 
computational indistinguishability through the notion of outcome 
indistinguishability where a predictor can be viewed as giving a model 
of events that cannot be refused from empiric evidence within some 
computational bound.

While differently motivated, this alternative paradigm for training 
predictors gives unexpected consequences, including:

1. 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.

2. A computational perspective on the meaning of individual probabilities.

3. A rigorous new paradigm for loss minimization in machine learning, 
through the notion of omni predictors, that simultaneously applies to a 
wide class of loss-functions, allowing the specific loss function to be 
ignored at the time of learning.

4. 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, Gal Yona