Course Home Page for Ethical Algorithm Design (CIS 4230/5230) University of Pennsylvania, Spring 2023 (original) (raw)
Ethical Algorithm Design CIS 4230/5230
Spring 2023
Tuesdays and Thursdays 10:15 11:45AM ET
Annenberg 110
Instructor:
Prof. Michael Kearns
mkearns@cis.upenn.edu
Office hours: Tuesday right after class until 1PM, in the lobby area right outside Annenberg 110 or by appointment
Teaching Assistants:
Neha Dohare
neha75@seas.upenn.edu
Office hours: Wednesday 10:30-11:30AM in Levine 5th floor bump space or by appointment
Declan Harrison
declanh@seas.upenn.edu upenn.edu
Office hours: Thursday 9-10AM in 4th floor 3401 Walnut or by appointment
Natalie Ho
natabnho@sas.upenn.edu
Office hours: Wednesday 5-6PM in GRW 5th floor bump space or by appointment
Jordan Hochman
jhawkman@seas.upenn.edu
Office hours: Thursday 5:15-6:15PM in GRW 5th floor bump space or by appointment
Aakash Jajoo
aakashj1@seas.upenn.edu
Office hours: Tuesday 1:45-2:45PM in Levine 5th floor bump space 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 in2021, 2020and2019.The first formal offering of the course was inSpring 2022.
Here are the lecture videosfrom the last pilot version. 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 a mixture of quizzes, coding assignments, written homeworks, and a written midterm and final.
CIS 423/523 fulfills theSEAS Engineering Ethics Requirementfor these programs: ASCS, BE, CMPE, CSCI, DMD and NETS (but you should confirm with your academic adivsor to be certain).
| Lecture Dates | Topic | Slides, Readings, Assignments, Announcements |
|---|---|---|
| Thu Jan 12 | Course Introduction and Overview | Lecture Notes A general-audience introduction to some of the themes of the course is given in the (recommended but not required) bookThe 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 17Tue Jan 19 | Foundations of Machine Learning | Lecture Notes |
| Thu Jan 24Tue Feb 26 | Bias in Machine Learning: COMPAS and ProPublica | Lecture Notes The following readings are required; you should read the two ProPublica pieces before the Jan 24 lecture so we can discuss them then. ProPublica article on COMPAS ProPublica analysis Practitioner's Guide to COMPAS Core(no need to read, but we'll peruse a bit together in lecture) 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) |
| Tue Jan 31Thu Feb 2Tue Feb 7Thu Feb 9Tue Feb 14Thu Feb 16Tue Feb 21 | Science of Fair ML: Models and Algorithms | Lecture Notes Readings: Inherent Trade-Offs in the Fair Determination of Risk Scores.J. Kleinberg, S. Mullainathan, M. Raghavan. (First 8 pages required) The Frontiers of Fairness in Machine Learning.Alexandra Chouldechova, Aaron Roth. (Required)Please play around with the followingGoogle demo site on fairness and ML.(Required) Equality of Opportunity in Supervised Learning.M. Hardt, E. Price, N. Srebro. (Intro required, rest optional; this is the post-processing/bolt-on method) A Reductions Approach to Fair Classification.A. Agarwal, A. Beygelzimer, M. DudÃk, J. Langford, H. Wallach. (Intro required, rest optional; this is the in-processing/constrained optimization/game theory method) An Empirical Study of Rich Subgroup Fairness for Machine Learning.MK, S. Neel, A. Roth, S. Wu. (Intro required, rest optional; this the rich subgroup/preventing fairness gerrymandering method) An Algorithmic Framework for Bias Bounties.I. Globus-Harris, MK, A. Roth. (Read at least the Intro and Sections 5 and 6, which preview your upcoming group project) |
| Thu Feb 23Tue Feb 28Thu Mar 2Tue Mar 14Tue Mar 21Thu Mar 23Tue Mar 28Thu Mar 30Tue Apr 4 | Differential Privacy and Related Topics | Lecture Notes Readings: Confidence-ranked reconstruction of census microdata from published statistics.T. Dick, C. Dwork, MK, T. Liu, A. Roth, G. Vetri, S. Wu. (Read Abstract/Intro and Sections A,B,C) |
| Tue Mar 7Thu Mar 9 | Spring Break, no lectures | . |
| Thu Mar 16 | Midterm Exam (in person, written, closed book/notes) | . |
| Last Two Weeks of Lecture | Ethical Algorithm Design in the Generative Era | Lecture Notes |