← List all talks ...

Contextual Search in the Presence of Irrational Agents

Chara Podimata – Graduate Student, Harvard

Thu, 6-Jan-2022 / 4:00pm / Packard 101

Abstract

Contextual search is a generalization of binary search in higher dimensions, which captures settings such as feature-based dynamic pricing. Standard game-theoretic formulations of this problem assume that agents act in accordance with a specific behavioral model. In practice, however, some agents may not follow the dominant behavioral model or they may act in ways that seem to be arbitrarily irrational. Existing algorithms heavily depend on the behavioral model being (approximately) accurate for all agents and have poor performance in the presence of even a few such arbitrarily irrational agents. In this talk, I provide a framework for studying contextual search when some of the agents can behave in ways inconsistent with the underlying behavioral model. The algorithms that I will present attain near-optimal regret guarantees in the absence of irrational agents and their performance degrades gracefully with the number of such agents.

The talk will be based on joint works with Thodoris Lykouris, Akshay Krishnamurthy, Robert Schapire, Renato Paes Leme, and Jon Schneider.

Bio

Chara Podimata is a final year PhD student in the EconCS group at Harvard, where she is advised by Yiling Chen. Her research studies incentive-aware Machine Learning algorithms for decision making, i.e., algorithms that adapt to the presence of strategic agents as data providers. Chara is supported by a Microsoft Dissertation Grant and a Siebel Scholarship. During her PhD, she interned twice at MSR NYC (mentored by Jennifer Wortman Vaughan and Aleksandrs Slivkins) and once at Google Research NYC (mentored by Renato Paes Leme). She has given tutorials related to strategic learning at EC20 and FAccT21. Outside of research, she spends her time training and adventuring with her pup, Terra.