CS Colloquium
Speaker: Nisheeth Vishnoi
Title: Algorithms and Bias
Host: Dan Spielman
Abstract:
Bias is an increasingly observed phenomenon in the world of machine learning (ML) and artificial intelligence (AI): From gender bias in image search, racial bias in court bail pleas, to biases in worldviews depicted in personalized newsfeeds. At the core, what is powering today’s AI/ML are algorithms for fundamental computational problems such as classification, data summarization, ranking, and online learning. Such algorithms have traditionally been designed with the goal of maximizing some notion of “utility” and identifying or controlling bias in their output has not been a consideration. As a consequence, they have the ability to pass (or even worsen) the bias from the input to the output. I will explain the emergence of bias in algorithmic decision making and address some of the challenges towards developing a systematic algorithmic framework to control biases in the aforementioned problems. As a concrete example, I will focus on the problem of data summarization and show how the pursuit of “unbiased” algorithms for this problem has led to new connections between entropy, continuous optimization, polynomials, resulting in advances at the core of theoretical computer science.