Title: Human Aspects of Machine Learning

Samira Samadi

Ph.D. Student

School of Computer Science

College of Computing

Georgia Institute of Technology

http://www.samirasamadi.com

Date: Thursday, November 29th, 2018

Time: 9:30am to 11am (EDT)

Location: KACB 3402

Committee:

Dr. Santosh Vempala (Advisor, School of Computer Science, Georgia Institute of Technology)

Dr. Mohit Singh (School of Computer Science, Georgia Institute of Technology)

Dr. Jamie Morgenstern (School of Computer Science, Georgia Institute of Technology)

Abstract:

As humans are inevitably being influenced by machine learning algorithms, it is crucial to study the human aspects of these algorithms. In this proposal, I investigate several ML paradigms from the viewpoint of  human usability and fairness. In the first line of work, I present the first usability study of humanly computable password strategies -- mental algorithms proposed by Blum and Vempala to help people calculate, in their heads, passwords for different websites without dependence on third-party tools or external devices. In the second line of work, I study fairness for Principal Component Analysis (PCA), one of the most commonly used dimensionality reduction techniques. We show on real-world data sets that PCA can inadvertently produce low-dimensional representations with different fidelity for two different populations (e.g., men and women). We define the notion of Fair PCA and present a polynomial-time algorithm for finding a low-dimensional representation of the data which is nearly-optimal with respect to this measure. Finally, I will discuss two of my ongoing projects: (a) spectral clustering with the fairness constraint that each population should have approximately equal representation in every cluster, and (b) fair interpretable classifiers for structured outcomes.