- Time: Tuesday, June 30, 10:30-11:30
- Title: From Cryptography to ML Theory and Practice
- Abstract: TBA
- Bio:
Shafi Goldwasser is the C. Lester Hogan Professor in Electrical Engineering and Computer Sciences at UC Berkeley, the Leighton family Professor of Mathematics at MIT and an Emeritus professor at the Computer science and applied mathematics department at the Weizmann Institute of Science in Israel. She was a director of the Simons Institute for the Theory of Computing, and is a co-founder and chief scientist of Duality Technologies. Goldwasser received a BS in applied mathematics from Carnegie Mellon University in 1979, and MS and PhD in computer science from UC Berkeley in 1984. Goldwasser was the recipient of ACM Turing Award for 2012. She was also the recipient of the Gödel Prize in 1993 and another in 2001 for her work on interactive proofs and connections to approximation, and was awarded the ACM Grace Murray Hopper Award (1996), the RSA award in mathematics (1998), the ACM Athena award for women in computer science (2008), the Benjamin Franklin Medal in Computer and Cognitive Science (2010), the IEEE Emanuel R. Piore Award (2011), the Barnard College Medal of Distinction (2016), and the Suffrage Science Award (2016). She is a member of the AAAS, ACM, NAE, NAS, Israeli Academy of Science, London Mathematical Society, Royal Society, and Russian Academy of Science.
- Time: Wednesday, July 1, 10:35-11:35
- Title: Learnability of Complex Objects in Modern AI
- Abstract: As machine learning and AI systems become increasingly pervasive and are deployed in high-stakes domains, developing theoretical foundations to understand and analyze their behavior has become more challenging, yet more pressing than ever before. Modern AI systems learn sophisticated structures that far exceed the analytical reach of classical learning theory and increasingly operate in environments where learning occurs in the presence of other learners.
In this talk, I will present new directions in learning theory that provide principled guarantees for increasingly complex AI systems. I will discuss general learnability guarantees for rich structured objects based on dual function classes and show how they apply to a broad range of settings, including using machine learning for algorithm design and automating hyperparameter tuning for machine learning itself. Finally, I will highlight emerging challenges for learning in the presence of other learners, spanning both cooperative settings and competitive strategic interactions.
- Bio: Maria-Florina Balcan is the Cadence Design Systems Professor of Computer Science in the School of Computer Science at Carnegie Mellon University. Her main research interests are machine learning, artificial intelligence, theory of computing, algorithmic game theory, and connections between learning theory and other scientific fields. She is a Simons Investigator, an ACM Fellow, an AAAI Fellow, a Sloan Fellow, a Microsoft Research New Faculty Fellow, and the recipient of the ACM Grace Murray Hopper Award, NSF CAREER award, paper awards in UAI, COLT, and ACM-EC, and several other industry awards. She has given distinguished lectures and invited keynote talks across different research fields (including machine learning, information theory, mathematics, algorithmic game theory, and operations research). She has co-chaired major conferences in the field: the Conference on Learning Theory (COLT) 2014, the International Conference on Machine Learning (ICML) 2016, and Neural Information Processing Systems (NeurIPS) 2020. She was also the general chair for the International Conference on Machine Learning (ICML) 2021 and a board member of the International Machine Learning Society.
- Time: Thursday, July 2, 10:35-11:35
- Title: Convex Analysis at Infinity: An Introduction to Astral Space
- Abstract: Not all convex functions have finite minimizers; some can only be minimized by a sequence as it heads to infinity, making it much harder, for instance, to prove convergence. This work develops an expansive new theory for understanding such minimizers at infinity, introducing astral space, a compact extension of Euclidean space to which such points at infinity have been added. Astral space is constructed to be as small as possible while still ensuring that all linear functions can be continuously extended to the new space. Astral space is especially compatible with standard convex analysis and is meant to provide the foundation for a more complete theory. Although not a vector space, nor even a metric space, astral space is nevertheless so well-structured as to allow useful and meaningful extensions of the most important concepts from convex analysis, including convexity of sets and functions, conjugacy, separation theorems, subdifferentials, as well as central topics from optimization and applications. Applied to widely used algorithms, these tools afford simplified proofs of convergence, even when the only minimizers are at infinity.
This is joint work with Miroslav Dudík and Matus Telgarsky. For further reading, see aka.ms/astral.
- Bio: Robert Schapire is a Partner Researcher at Microsoft Research in New York City. He received his PhD from MIT in 1991. After a short post-doc at Harvard, he joined the technical staff at AT&T Labs (formerly AT&T Bell Laboratories) in 1991. In 2002, he became a Professor of Computer Science at Princeton University. He joined Microsoft Research in 2014. His awards include the 1991 ACM Doctoral Dissertation Award, the 2003 Gödel Prize, and the 2004 Kanelakkis Theory and Practice Award (both of the last two with Yoav Freund). He is a fellow of the AAAI, and a member of both the National Academy of Engineering and the National Academy of Sciences. His main research interest is in theoretical and applied machine learning. He is the co-author most recently of Astral Space: Convex Analysis at Infinity.