works on

From the 1 of 34 linked papers with an AI index.

activity
20162025
most citedFine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

256 citations · 486 across the 26 of their papers we have counts for

collaborators
Showing 2019Show all

6 papers · 1 filter

cs.LG2019★ 43 cited

An Exponential Learning Rate Schedule for Deep Learning

Zhiyuan Li, Sanjeev Arora

Intriguing empirical evidence exists that deep learning can work well with exoticschedules for varying the learning rate. This paper suggests that the phenomenon may be due to Batc…

cs.LG2019★ 77 cited

Enhanced Convolutional Neural Tangent Kernels

Zhiyuan Li, Ruosong Wang, Dingli Yu +4

Recent research shows that for training with loss, convolutional neural networks (CNNs) whose width (number of channels in convolutional layers) goes to infinity correspon…

cs.LG2019★ 13 cited

Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

Sanjeev Arora, Simon S. Du, Zhiyuan Li +3

Recent research shows that the following two models are equivalent: (a) infinitely wide neural networks (NNs) trained under l2 loss by gradient descent with infinitesimally small l…

cs.LG2019

Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee

Wei Hu, Zhiyuan Li, Dingli Yu

Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data. Such over-fitting ability hinders generalization whe…

cs.LG2019

On Exact Computation with an Infinitely Wide Neural Net

Sanjeev Arora, Simon S. Du, Wei Hu +3

How well does a classic deep net architecture like AlexNet or VGG19 classify on a standard dataset such as CIFAR-10 when its width --- namely, number of channels in convolutional l…

cs.LG2019★ 256 cited

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

Sanjeev Arora, Simon S. Du, Wei Hu +2

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization f…