Theory


  • S&DS Seminar: Jingfeng Wu (Berkeley), “Gradient Descent Dominates Ridge: A Statistical View on Implicit Regularization”

    Talk summary: A key puzzle in deep learning is how simple gradient methods find generalizable solutions without explicit regularization. This talk discusses the implicit regularization of gradient descent (GD) through the lens of statistical dominance. Using least squares as a clean proxy, we present two surprising findings.  First, GD dominates ridge regression. For any well-specified…


  • FDS Colloquium: Bento Natura (Columbia), “Faster Exact Linear Programming”

    Optional Zoom link: https://yale.zoom.us/j/99342713421 Abstract: We present a novel algorithm to solve various subclasses of linear programs, with a particular focus on strongly polynomial algorithms—those that operate in polynomial time relative to the problem’s dimension. Although subclasses like bipartite matching and maximum flow are known to be solvable in strongly polynomial time, the existence of…



  • S&DS Seminar: Yiling Chen (Harvard), “Strategic Design to Improve Information Integrity”

    Speaker: Yiling ChenGordon McKay Professor of Computer ScienceJohn A. Paulson School of Engineering & Applied SciencesHarvard UniversityWebsite: https://seas.harvard.edu/person/yiling-chen Monday, April 15, 20243:30 pm – Pre-talk meet and greet teatime (FDS Kitchen)4:00 pm – Talk (FDS Seminar Room #1327)at the Yale Institute for Foundations of Data Science, Kline Tower, 13th Floor Virtual Link : https://yale.zoom.us/j/94223816617 (Zoom…


  • Amin Karbasi

    Amin Karbasi granted 2024 Roberts Innovation Fund Award

    Amin Karbasi (Member) and his Postdoctoral Associate Insu Han, along with their collaborator Amir Zandieh (Max Planck Institute), were recipients of a 2024 Roberts Innovation Fund Award for their research on making AI more powerful and cost effective. The Roberts Innovation Fund, managed by Yale Ventures, are awarded to 10 faculty-led projects in the School…


  • Yale Theory Student Seminar: Heejune Sheen, “Implicit Regularization of Gradient Flow for One-layer Softmax Attention”

    This is a place for theory-minded people to gather for a weekly lunch seminar. This semester (spring 24), we (mostly) meet on Thursdays at 11:45 (for lunch) and the talk starts at 12:00. The presentations are on papers, results, conjectures, or anything theory-oriented. In order to keep things more casual and interactive, presentations are on…