conftrace_

mean-field limit

6 papers

Explore in graph

Co-occurring keywords

wasserstein gradient flow (35) gradient flow (142) stochastic gradient descent (1091) weight decay regularization (6) stochastic differential equation (181) weight decay (50) shallow neural network (18) transformer training (13) two-layer network (11) high-dimensional limit (2)

Papers

Global Convergence in Training Large-Scale Transformers NIPS 2024
Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent JMLR 2024
Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces ICML 2023
From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks COLT 2023
Stochastic Approximation Algorithms for Systems of Interacting Particles NIPS 2023
A Dynamical Central Limit Theorem for Shallow Neural Networks NIPS 2020