Topics in Deep Learning Theory
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesTopics in Deep Learning Theory Eli Grigsby
Topics in Deep Learning Theory Eli Grigsby
Quantum Field Theory and Physical Mathematics Seminar Speaker: Brian Williams, Boston University Title: Dolbeault Virasoro algebra and M5 branes Abstract: The worldvolume theory on a stack of M5 branes in M-theory is superconformal. We propose a conjecture that in the holomorphic twist of the theory on a stack of M5 branes an infinite-dimensional enhancement of […]
Math and Machine Learning Program Discussion
Member Seminar Speaker: Keyou Zeng Title: Scattering Amplitude from a Twistor Point of View Abstract: Scattering amplitude is a key quantity in quantum field theory. Although challenging to compute at higher loops and for large particle numbers, physicists have developed various tools to gain a deeper understanding of amplitudes. In this seminar, I will introduce […]
Full Name Role Office # Affiliation Dates Email Address Last Name Alberto Bietti Researcher Flatiron Institute Alberto@Bietti.me Bietti Francois Charton Math AI Organizer 202 Meta AI fcharton@meta.com Charton Alex Davies Machine Learning Specialist DeepMind adavies@google.com Davies Noam Elkies Professor Harvard University elkies@math.harvard.edu Elkies Drew Sutherland Math AI Organizer 202 MIT drew@math.mit.edu Sutherland Tristan Buckmaster Math […]
Math and Machine Learning Program Discussion
General Relativity Seminar Speaker: Christoph Kehle, MIT Title: Gravitational collapse to extremal Reissner-Nordström and the third law of black hole thermodynamics Abstract: In this talk, I will present a proof that extremal Reissner-Nordström black holes can form in finite time in gravitational collapse of charged matter. In particular, this construction provides a definitive disproof of […]
Topics in Deep Learning Theory Eli Grigsby
Geometry and Quantum Theory Seminar Speaker: Mayuko Yamashita, Kyoto University Title: Topological Modular Forms, its equivariant refinements and relation with supersymmetric quantum field theories Abstract: This talk is about the Segal-Stolz-Teichner program, which is one of the most deep and interesting topics relating homotopy theory and physics. Mathematically, they propose a geometric model of TMF, […]
Math and Machine Learning Program Discussion
CMSA Q&A Seminar Speaker: Nazim Bouatta (HMS) Topic: What are AlphaFold2 and OpenFold
New Technologies in Mathematics Seminar Speaker: Anirudh Goyal (University of Montreal) Title: From Word Prediction to Complex Skills: Data Flywheels for Mathematical Reasoning Abstract: This talk examines how large language models (LLMs) evolve from simple word prediction to complex skills, with a focus on mathematical problem solving. A major driver of AI products today is the fact […]