Plenary Speakers

Vitaly Feldman (Apple)

Title: TBD

Abstract: TBD

Bio: Vitaly Feldman is a research scientist at Apple working on foundations of machine learning and privacy-preserving data analysis. His recent research interests include the role of memorization in learning, distributed privacy-preserving learning, privacy-preserving optimization, tools for analysis of generalization, and adaptive data analysis

Vitaly holds a Ph.D. from Harvard (2006, advised by Leslie Valiant) and was previously a research scientist at Google Research (Brain team) and IBM Research – Almaden (Theory group). His work on understanding of memorization in learning was recognized by the 2021 Caspar Bowden Award for Outstanding Research in Privacy Enhancing Technologies. His research on foundations of adaptive data analysis was recognized by the ACM STOC 2025 Test of Time award. His works were also recognized by COLT Best Student Paper Award in 2005 and 2013 (student co-authored) and by the IBM Research Best Paper Award in 2014, 2015 and 2016. He served as a program co-chair for COLT 2016 and ALT 2021 conferences and as a co-organizer of the Simons Institute Program on Data Privacy in 2019.

Surbhi Goel (University of Pennsylvania)

Title: TBD

Abstract: TBD

Bio: Surbhi Goel is the Magerman Term Assistant Professor of Computer and Information Science at University of Pennsylvania. She is affiliated with the Theory group, the ASSET center on safe, explainable, and trustworthy AI systems, and the Warren Center for network and data sciences. She is the co-founder of Learning Theory Alliance (LeT-All), a community building and mentorship initiative and recently co-organized the Special Year of Large Language Models at the Simons Institute for the Theory of Computation. She is the recipient of the Schmidt Sciences AI2050 Early Career Fellowship, an Amazon Research Award, the Bert Kay Dissertation award from UT Austin, a JP Morgan AI Fellowship, a Simons-Berkeley Research Fellowship, and Rising Star recognition in both ML and EECS. Her research interests lie at the intersection of theoretical computer science and machine learning, with a focus on developing theoretical foundations for safe, reliable, and trustworthy AI. 

Aaron Roth (University of Pennsylvania)

Title: Agreement and Alignment for Human-AI Collaboration

Abstract: As AI models become increasingly powerful, it is an attractive proposition to use them in important decision-making pipelines in collaboration with human decision-makers. But how should a human being and a machine learning model collaborate to reach decisions that are better than either of them could achieve on their own? If the human and the AI model were perfect Bayesians, operating in a setting with a commonly known and correctly specified prior, Aumann’s classical agreement theorem would give us one answer: They could engage in conversation about the task at hand, and their conversation would be guaranteed to converge to (accuracy-improving) agreement. This classical result, however, would require making many implausible assumptions, both about the knowledge and computational power of both parties. We show how to recover similar (and more general) results using only computationally and statistically tractable assumptions, which substantially relax full Bayesian rationality. In the second part of the talk, we go on to consider a more delicate problem: that the AI model might be acting at least in part to advance the interests of its designer, rather than the interests of its user, which might be in tension. We show how market competition between different AI providers can mitigate this problem assuming only a mild “market alignment” assumption—that the user’s utility function lies in the convex hull of the AI providers’ utility functions—even when no single provider is well aligned. In particular, we show that in all Nash equilibria of the AI providers under this market alignment condition, the user is able to advance her own goals as well as they could have in collaboration with a perfectly aligned AI model. This talk describes the results of three papers—Tractable Agreement Protocols (2025 ACM Symposium on Theory of Computing), Collaborative Prediction: Tractable Information Aggregation via Agreement (ACM-SIAM Symposium on Discrete Algorithms), and Emergent Alignment from Competition—which are joint works with Natalie Collina, Ira Globus-Harris, Surbhi Goel,
Varun Gupta, Emily Ryu, and Mirah Shi.

Bio: Aaron Roth is the Henry Salvatori Professor of Computer and Cognitive Science, in the Computer and Information Sciences department at the University of Pennsylvania, with a secondary appointment in the Wharton statistics department. He is affiliated with the Warren Center for Network and Data Science, and co-director of the Networked and Social Systems Engineering (NETS) program.  He is also an Amazon Scholar at Amazon AWS. He is the recipient of the Hans Sigrist Prize, a Presidential Early Career Award for Scientists and Engineers (PECASE), an Alfred P. Sloan Research Fellowship, an NSF CAREER award, and research awards from Yahoo, Amazon, and Google.  His research focuses on the algorithmic foundations of data privacy, algorithmic fairness, game theory, learning theory, and machine learning. Together with Cynthia Dwork, he is the author of the book “The Algorithmic Foundations of Differential Privacy.” Together with Michael Kearns, he is the author of “The Ethical Algorithm”.

Ohad Shamir (Weizmann Institute and University of Toronto)

Title: Some very old and very new problems in learning theory

Abstract: I will discuss recent progress on two open problems, which both tie together new and classical elements in learning theory and statistics. The first is about the effect of AI slop on learning algorithms, and what it has to do with analyses of maximum likelihood from the 1940’s. The second will involve a rant about (mis)-interpretations of the well-known Statistical Queries model, and whether we really understand why some learning problems are hard with gradient-based methods. Based on joint works with Daniel Barzilai and Itamar Shoshani.

Bio: Ohad Shamir is a professor at the Weizmann Institute of Science, and a visiting professor at the University of Toronto, with previous research roles at Microsoft and Google. His work focuses on theoretical machine learning, in areas such as theory of deep learning, the intersection of machine learning and optimization, and learning under information and communication constraints. He served as a program co-chair of the Conference on Learning Theory (COLT), as well as a member of its steering committee, and as an action editor of the Journal of Machine Learning Research (JMLR). His honors include the inaugural 2024 Prize in the Mathematics of Artificial Intelligence, several best paper awards, the Hebrew University’s PhD thesis prize, and a €1.5 million ERC grant.