Skip to content
conftrace_

dynamical mean field theory

8 papers

Explore in graph

Also known as

DMFT

Co-occurring keywords · papers mentioning both

gradient descent (3) learning dynamics (2) neural network optimization (2) feature learning (2) initialization variance (1) finite-width correction (1) kernel variance (1) gaussian mixture classification (1) transformer dynamics (1) scaling limit (1)

Papers

High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks JMLR 2026 Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method COLT 2026 Infinite Limits of Multi-head Transformer Dynamics NeurIPS 2024 The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents ICML 2024 Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks NeurIPS 2023 The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks ICLR 2023 Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems NeurIPS 2021 Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification NeurIPS 2020