As algorithmic decisions and likelihood predictions reach ever more deeply, and with increasing consequence, into our lives, there is an increasing mandate that they be “fair”. This program comprises a short course on the theory of algorithmic fairness taught by Dwork and Rothblum, followed by a workshop, Who Counts?, on sex and gender bias in data, organized by Benjamin, Dwork, and Williams.
The Course (July 11-15, 2022): After an investigation of an array of “first wave” fairness definitions and their behaviors under composition, the course will highlight a class of desiderata that aim to bridge the gap between statistical and individual fairness notions and examine the meaning of likelihood predictions through the lens of complexity theory. Attention will be paid to open fairness questions surrounding the choice of data by which individuals are represented to the algorithm, and the proxies used for outcomes, the fairness desiderata, and the pressing problem of moving from algorithms that reproduce the world as it is to algorithms that lead us to a more ideal world. The course will end with a deeper look into 1-2 application areas.
The workshop (July 17-20, 2022): Who Counts? Machine learning algorithms learn from training data; when these are biased so are the algorithms they produce. The workshop will examine sources of sex and gender bias in data, with emphases on impoverished women; women of color; trans and non-binary persons; and older women.
Cynthia Dwork (Harvard University)
Guy Rothblum (Weizmann Institute of Science)
Patricia Williams (Northeastern University)