activity
20172021
most citedMean Field Limit of the Learning Dynamics of Multilayer Neural Networks

35 citations · 45 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG20211 cited

Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training

Huy Tuan Pham, Phan-Minh Nguyen

The mean field (MF) theory of multilayer neural networks centers around a particular infinite-width scaling, where the learning dynamics is closely tracked by the MF limit. A rando…

cs.LG2021

Global Convergence of Three-layer Neural Networks in the Mean Field Regime

Huy Tuan Pham, Phan-Minh Nguyen

In the mean field regime, neural networks are appropriately scaled so that as the width tends to infinity, the learning dynamics tends to a nonlinear and nontrivial dynamical limit…

cs.LG20217 cited

Analysis of feature learning in weight-tied autoencoders via the mean field lens

Phan-Minh Nguyen

Autoencoders are among the earliest introduced nonlinear models for unsupervised learning. Although they are widely adopted beyond research, it has been a longstanding open problem…

cs.LG20201 cited

A Note on the Global Convergence of Multilayer Neural Networks in the Mean Field Regime

Huy Tuan Pham, Phan-Minh Nguyen

In a recent work, we introduced a rigorous framework to describe the mean field limit of the gradient-based learning dynamics of multilayer neural networks, based on the idea of a…

cs.LG201935 cited

Mean Field Limit of the Learning Dynamics of Multilayer Neural Networks

Phan-Minh Nguyen

Can multilayer neural networks -- typically constructed as highly complex structures with many nonlinearly activated neurons across layers -- behave in a non-trivial way that yet s…

cs.IT20171 cited

State Evolution for Approximate Message Passing with Non-Separable Functions

Raphael Berthier, Andrea Montanari, Phan-Minh Nguyen

Given a high-dimensional data matrix , Approximate Message Passing (AMP) algorithms construct sequences of vectors ${\boldsymbol u}^t\in{…