Seminar: Algorithms in the AI Age: Fair and Learning-Augmented
Ali Vakilian
Research Assistant Professor
TTIC
Wednesday, January 22
9:30 - 10:30AM
1100 Torgersen Hall
Abstract
The widespread deployment of AI across diverse applications presents promising opportunities while simultaneously raising significant societal concerns. Motivated by these opportunities and challenges, in this talk I will focus on two key research directions in the intersection of algorithms and machine learning: “learning-augmented” algorithms, and fairness of algorithms and machine learning.
The growing use of automated decision making in high-stake tasks such as hiring and criminal justice, has led to an extensive line of research on the societal and ethical aspects of algorithms and machine learning. In particular, the design of fair clustering techniques has received considerable attention in the past few years. I will describe my works on the design of efficient algorithms for fair clustering under several notions, such as “proportional representation” within clusters or centers, and the notion of “equitable access” to facilities.
In learning-augmented algorithms, the goal is to exploit the existing patterns in the data to improve the performance of classical algorithms. More specifically, it has the following promise: when provided with accurate (machine-learned) predictions about the input, it provably surpasses the performance of classical algorithms. On the other hand, even if the predictions are adversarial, it still provides almost matching worst-case guarantees as the best classical algorithms. In this work, I will overview some of my works that initiated the study of learning-augmented algorithms in the streaming model, and provide such algorithms for fundamental problems in this domain including frequency estimation and low-rank approximation.
Biography
Ali Vakilian is a Research Assistant Professor at TTIC. His research interests include fairness of algorithms and machine learning, learning-augmented algorithms, and algorithms for massive data. Ali received his Ph.D. from MIT EECS, where he was advised by Erik Demaine and Piotr Indyk. He completed his MS studies at UIUC where he was a recipient of the Siebel Scholar award. He is a recipient of the Outstanding Student Paper Highlight Award at AISTATS 2024. For more information, visit his website at http://www.mit.edu/~vakilian/.