Course Identification

FAT Algorithms: Fairness, Accountability and Transparency in automated decisions
20184142

Lecturers and Teaching Assistants

Prof. Moni Naor
N/A

Course Schedule and Location

2018
Second Semester
Monday, 16:15 - 18:00, Ziskind, Rm 1
19/03/2018

Field of Study, Course Type and Credit Points

Mathematics and Computer Science: Lecture; Elective; 2.00 points

Comments

N/A

Prerequisites

No

Restrictions

50

Language of Instruction

English

Attendance and participation

Expected and Recommended

Grade Type

Numerical (out of 100)

Grade Breakdown (in %)

30%
40%
30%

Evaluation Type

Final assignment

Scheduled date 1

N/A
N/A
-
N/A

Estimated Weekly Independent Workload (in hours)

N/A

Syllabus

The goal of the course is to explore quantitative approaches to
fairness, especially issues related to recent applications of
algorithmic techniques to determine social and human related
decisions. As background material we will  cover (cooperative) Game
Theory, Cryptography, Differential Privacy (previous semester course)
Machine Learning and then consider the issues in various settings

Battling Algorithmic Bias By Keith Kirkpatrick, CACM 2016 No. 10,
Pages 16-17 https://cacm.acm.org/magazines/2016/10/207759-battling-algorithmic-bias/fulltext

DP Style:
* Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, Rich
Zemel, Fairness Through Awareness

* Richard Zemel, Yu (Ledell) Wu, Kevin Swersky, Toniann Pitassi,
Cynthia Dwork, Learning Fair Representation,
https://www.cs.toronto.edu/~toni/Papers/icml-final.pdf

* Shokri and Shamtikov, Membership Inference Attacks Against Machine
Learning Models http://www.cs.cornell.edu/~shmat/shmat_oak17.pdf

DISCRIMINATION

* Jon Kleinberg, Sendhil Mullainathan, Manish Raghavan, Inherent
Trade-offs in the Fair Determination of Risk Scores
https://arxiv.org/abs/1609.05807

* Alexandra Chouldechova, Fair prediction with disparate impact: A
study of bias in recidivism prediction instruments,
https://arxiv.org/abs/1703.00056


* Ke Yang, Julia Stoyanovich, Measuring Fairness in Ranked Outputs
https://arxiv.org/abs/1610.08559

Bias in learning based on DB:

* Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, Adam Kala
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word
Embeddings, https://arxiv.org/abs/1607.06520

* Aylin Caliskan-Islam , Joanna J. Bryson and Arvind Narayanan,
Semantics derived automatically from language corpora necessarily
contain human biases
http://randomwalker.info/publications/language-bias.pdf

Interpretable ML
Benjamin Letham, Cynthia Rudin, Tyler H. McCormick, David Madigan,
Interpretable classifiers using rules and Bayesian analysis: Building
a better stroke prediction model


CRYPTO RELATED

MPC and Fairness
*Cleve, Gordon HKL

* Bitcoin and blockchain

* Accoutable Algorithms, Kroll and Felten
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2765268
https://www.youtube.com/watch?v=mTNV0QI1cg4

Papers to criticize:
http://www.pnas.org/content/110/15/5802.full

Courses: Suresh Venkat https://geomblog.github.io/fairness/

Moritz Hardt https://fairmlclass.github.io/

 

Learning Outcomes

Upon successful completion of this course students should be able to: 

Analyze algorithms and systems using the methodology explored in the course.

Reading List

N/A

Website