Today
  • Featured

    Mathematics and Machine Learning Closing Workshop

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    Mathematics and Machine Learning Closing Workshop Dates: October 28 - Oct. 30, 2024 Location: Room G10, CMSA, 20 Garden Street, Cambridge MA The closing workshop will provide a forum for discussing the most current research in these areas, including work in progress and recent results from program participants. We will devote one day to frontier […]

  • Formality Theorem and Webs

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    Member Seminar Speaker: Ahsan Khan Title: Formality Theorem and Webs Abstract: The “formality theorem” of Kontsevich was a key result that implies that every Poisson manifold admits a deformation quantization. I will review the ideas behind the formality theorem and discuss a potentially novel viewpoint on it involving webs and twisted masses.

  • The spin-statistics theorem for TFTs

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    Quantum Field Theory and Physical Mathematics Seminar Speaker: Luuk Stehouwer, Dalhousie University Title: The spin-statistics theorem for TFTs Abstract: In quantum field theory (QFT) the spin-statistics theorem says that in a unitary QFT, a particle has half-integer spin if and only if it is a fermion. I show how to phrase this statement in the […]

  • Topics in Deep Learning Theory

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    Topics in Deep Learning Theory Eli Grigsby

  • How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    https://youtu.be/C6NDdnSaluU New Technologies in Mathematics Seminar Speaker: Aryo Lotfi (EPFL) Title: How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad Abstract: Can Transformers predict new syllogisms by composing established ones? More generally, what type of targets can be learned by such models from scratch? Recent works show that Transformers can be Turing-complete in terms of […]

  • Topics in Deep Learning Theory

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    Topics in Deep Learning Theory Eli Grigsby

  • Higher Vapnik–Chervonenkis theory

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    Colloquium Speaker: Artem Chernikov, University of Maryland Title: Higher Vapnik–Chervonenkis theory Abstract: Finite VC-dimension, a combinatorial property of families of sets, was discovered simultaneously by Vapnik and Chervonenkis in probabilistic learning theory, and by Shelah in model theory (where it is called NIP). It plays an important role in several areas including machine learning, combinatorics, mathematical […]

  • Positive mass and rigidity theorems in Riemannian geometry  

    CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United States

    Member Seminar Speaker: Puskar Mondal Title: Positive mass and rigidity theorems in Riemannian geometry Abstract: Positive mass theorem proved by Schoen-Yau, Witten, Taubes-Parker is one of the most important results in scalar curvature geometry in asymptotically flat settings. Since then several versions have been proven and generalized to other geometries such as asymptotically hyperbolic manifolds. The analogous […]