Ethical Algorithm Design
CIS 423/523
Spring 2022
Tuesdays and Thursdays 1:453:15PM ET
118 Fagin Hall
Instructor:
Prof. Michael Kearns
mkearns@cis.upenn.edu
Office hours (virtual): TBD
Teaching Assistants:
Ira GlobusHarris (they/them)
igh@seas.upenn.edu
Office hours: Virtual Wed 111
here
or by appointment.
Elizabeth Margolin
ecmargo@seas.upenn.edu
Office hours: Virtual Thu 111
here
or by appointment.
Course Description
This course is about the social and human problems that can arise from algorithms, AI and machine learning, and how we might design these technologies to be "better behaved" in the first place. It is first and foremost a science or engineering course, since we will be developing algorithm design principles. You can get a rough sense of course themes and topics by visiting the websites for the pilot versions of this course offered in 2021, 2020 and 2019
Here are the lecture videos from the pilot version from last year. Please note that they will not correspond exactly to this year's lectures, and should not be viewed as a substitute for mandatory lecture attendance.
Prerequisites: Familiarity with some machine learning, basic statistics and probability theory will be helpful. While this is not a theory class, you need to be comfortable with mathematical notation and formalism. There will be some simple coding and data analysis assignments, so some basic programming ability is needed.
Course content will include readings from the scientifc literature, the mainstream media and other articles and books.
Grades will be based on some TBD mixture of quizzes, coding assignments, possible a midterm and/or final, and perhaps a final project or book club.
Since at least the first couple of lectures will be virtual, here is the Zoom link for the live sessions.
CIS 423/523 fulfills the SEAS Engineering Ethics Requirement for these programs: ASCS, BE, CMPE, CSCI, DMD and NETS.
Lecture Dates 
Topic 
Slides, Readings, Assignments, Announcements 

Thu Jan 13 
Course Introduction and Overview 
Lecture video:
[Jan 13]
The first assignment of the semester is to complete this survey. A generalaudience introduction to some of the themes of the course is given in the (recommended but not required) book The Ethical Algorithm: The Science of Socially Aware Algorithm Design, by M. Kearns and A. Roth. Also recommended but not required: Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy, by C. O'Neil. 
Tue Jan 18 Tue Jan 25 
Foundations of Machine Learning 
Lecture videos:
[Jan 18]
There is good and comprehensive set of videos and readings related to many of the topics we covered in these lectures in this Google machine learning course. 
Thu Jan 27 Tue Feb 1 
Discrimination in Machine Learning: COMPAS and ProPublica 
The following readings are required; you should read the two ProPublica pieces before the Jan 25 lecture so we can discuss them then. COMPAS Risk Assesment Survey (just skim) Northpointe response to ProPublica ProPublica github repository, including dataset (we'll look at the dataset a bit in lecture)(technical, just skim) 
Thu Feb 3 Tue Feb 8 Thu Feb 10 Tue Feb 15 Thu Feb 17 Tue Feb 22 Thu Feb 24 
Science of Fair ML: Models and Algorithms 
Readings: Inherent TradeOffs in the Fair Determination of Risk Scores, J. Kleinberg, S. Mullainathan, M. Raghavan. (Read first 8 pages) The Frontiers of Fairness in Machine Learning. Alexandra Chouldechova, Aaron Roth. (Read entire article) Please play around with the following Google demo site on fairness and ML. Equality of Opportunity in Supervised Learning. M. Hardt, E. Price, N. Srebro. (Optional; this is the postprocessing/bolton method.) A Reductions Approach to Fair Classification. A. Agarwal, A. Beygelzimer, M. DudÃk, J. Langford, H. Wallach. (Optional; this is the inprocessing/constrained optimization/game theory method.) And here is a series of papers extending the gametheoretic approach to different/stronger notions of fairness (all optional): An Empirical Study of Rich Subgroup Fairness for Machine Learning. MK, S. Neel, A. Roth, S. Wu. Average Individual Fairness: Algorithms, Generalization and Experiments. MK, A. Roth, S. SharifiMalvajerdi. An Algorithmic Framework for Fairness Elicitation. C. Jung, MK, S. Neel, A. Roth, L. Stapleton, S. Wu. Minimax Group Fairness: Algorithms and Experiments Emily Diana, Wesley Gill, MK, Krishnaram Kenthapadi, Aaron Roth.

Tue Mar 1 Thu Mar 3 
"Bias Bounty" Project Introduction 
Here is the algorithmic ``bias bounty'' framework; it is recommended that you
take at least a highlevel reading for the coding project:
Beyond the Frontier: Fairness Without Accuracy Loss. I. GlobusHarris, MK, A. Roth.

Tue Mar 15 Thu Mar 17 Tue Mar 20 Thu Mar 22 
Algorithmic Privacy and Related Topics 
Lecture Notes
