Skip to content
conftrace_

infinite width scaling

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

modified flow (1) dynamical mean field theory (1) stochastic modified flow (1) transformer dynamics (1) scaling limit (1) infinite-width limit (1) stochastic differential equation (1) mean-field limit (1) neural network optimization (1) feature learning (1)

Papers

Infinite Limits of Multi-head Transformer Dynamics NeurIPS 2024 Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent JMLR 2024