paper-with-me

홈 › Papers

Mean Field Limit of the Learning Dynamics of Multilayer Neural Networks

2019-02-07 · 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 simplifies away a major part of their complexities? In this work, we uncover a phenomenon in which the behavior of these complex networks -- under suitable scalings and stochastic gradient descent dynamics -- becomes independent of the number of neurons as this number grows sufficiently large. We develop a formalism in which this many-neurons limiting behavior is captured by a set of equations, thereby exposing a previously unknown operating regime of these networks. While the current pursuit is mathematically non-rigorous, it is complemented with several experiments that validate the existence of this behavior.

📄 PDF Abstract BibTeX arXiv:1902.02880

Code (1)

npminh12/multilayer-mean-field tf

Similar Papers 제목 키워드 기반

A Rigorous Framework for the Mean Field Limit of Multilayer Neural Networks

2020-01-30 · Phan-Minh Nguyen, Huy Tuan Pham

We develop a mathematically rigorous framework for multilayer neural networks in the mean field regime. As the network's widths increase, the network's learning trajectory is shown to be well captured by a meaningful and…

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

2020-06-16 · 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 neuronal embedding. There we also proved…

Diversity

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

2021-10-29 · NeurIPS 2021 12 · 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 random fluctuation around this infinite-width…

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

2021-05-11 · ICLR 2021 1 · 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, known as the mean field limit. This le…

Depth Separation with Multilayer Mean-Field Networks

2023-04-03 · Yunwei Ren, Mo Zhou, Rong Ge

Depth separation -- why a deeper network is more powerful than a shallower one -- has been a major problem in deep learning theory. Previous results often focus on representation power. For example, arXiv:1904.06984 cons…

Learning Theory