Dynamical Mean Field Theory, Random Matrices and Learning in High Dimensions - YouTube
Speaker: Blake Bordelon, Harvard UniversityThis talk is part of the ProbAI Theory of Scaling Laws Workshop 2026, hosted at the Department of Statistics, Univ...
Speaker: Blake Bordelon, Harvard University This talk is part of the ProbAI Theory of Scaling Laws Workshop 2026, hosted at the Department of Statistics, University of Warwick. The workshop is jointly funded by the Centre for Research in Statistical Methodology (CRiSM) at Warwick statistics and Prob_AI Research Hub. The two rightmost boards were not recorded, but accompanying notes can be found on the workshop website: https://warwick.ac.uk/fac/sci/statistics/news/probai-scaling-laws-2026/programme/ It's my pleasure to introduce Blake Sar. So Blake is a postto at the Harvard mathematical…
saved by
related reading
- Training Dynamics in Large Networks: From Super-Wide to the Scaling Law Regimeyoutube.com
- MIA: Greg Yang, Tuning Large Neural Networks via Zero-Shot Hyperparameter Transferyoutube.com
- Statistical Mechanics of Deep Learningganguli-gang.stanford.edu
- [2205.09653] Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networksarxiv.org
- Dynamical Approach to RMT.pdfpeople.math.harvard.edu
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- Spin-Model Transformers | mcbalmcbal.github.io
- Step-by-Step Diffusion: An Elementary Tutorialarxiv.org
- [2304.03408] Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networksarxiv.org
- Generative Models and Physics | Yi Zhuang You (UCSD)youtube.com
- Statistical Physics for Ambitious Interpretability: A Workshop Retrospective — LessWronglesswrong.com
- Spring 2023 6.8210 Lecture 2: Nonlinear Dynamicsyoutube.com