activity
20182022
most citedExplicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks

31 citations · 32 across the 3 of their papers we have counts for

collaborators

9 papers

cs.LG20221 cited

Linear Stability Hypothesis and Rank Stratification for Nonlinear Models

Yaoyu Zhang, Zhongwang Zhang, Leyang Zhang +3

Models with nonlinear architectures/parameterizations such as deep neural networks (DNNs) are well known for their mysteriously good generalization performance at overparameterizat…

cs.LG2021

Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks

Yaoyu Zhang, Tao Luo, Zheng Ma +1

Why heavily parameterized neural networks (NNs) do not overfit the data is an important long standing open question. We propose a phenomenological model of the NN training to expla…

math.NA2020

Fourier-domain Variational Formulation and Its Well-posedness for Supervised Learning

Tao Luo, Zheng Ma, Zhiwei Wang +2

A supervised learning problem is to find a function in a hypothesis function space given values on isolated data points. Inspired by the frequency principle in neural networks, we…

cs.LG2020

On the exact computation of linear frequency principle dynamics and its generalization

Tao Luo, Zheng Ma, Zhi-Qin John Xu +1

Recent works show an intriguing phenomenon of Frequency Principle (F-Principle) that deep neural networks (DNNs) fit the target function from low to high frequency during the train…

cs.LG2020

Phase diagram for two-layer ReLU neural networks at infinite-width limit

Tao Luo, Zhi-Qin John Xu, Zheng Ma +1

How neural network behaves during the training over different choices of hyperparameters is an important question in the study of neural networks. In this work, inspired by the pha…

math.NA2020

Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory

Tao Luo, Haizhao Yang

The problem of solving partial differential equations (PDEs) can be formulated into a least-squares minimization problem, where neural networks are used to parametrize PDE solution…