Difan Zou

发表

Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks

Yuan Cao, Quanquan Gu, Difan Zou, 2018, ArXiv.

On the Global Convergence of Training Deep Linear ResNets pdf

Philip M. Long, Quanquan Gu, Difan Zou, 2020, ICLR.

STOCHASTIC GRADIENT DESCENT WITH MODERATE LEARNING RATE

Difan Zou, Jingfeng Wu, 2021 .

Sampling from Non-Log-Concave Distributions via Stochastic Variance-Reduced Gradient Langevin Dynamics

Quanquan Gu, Difan Zou, Pan Xu, 2019 .

How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks? pdf

Yuan Cao, Quanquan Gu, Zixiang Chen, 2019, ICLR.

On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients

Quanquan Gu, Difan Zou, Quanquan Gu, 2021, ICML.

1 Mbps Real-Time NLOS UV Scattering Communication A 1 Mbps Real-Time NLOS UV Scattering Communication System With Receiver Diversity Over 1 km

Difan Zou, Zhengyuan Xu, Guanchu Wang, 2018 .

Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States

Michael W. Dusenberry, Benjamin D. Trump, Long T. Le, 2022, Proceedings of the National Academy of Sciences of the United States of America.

The Benefits of Implicit Regularization from SGD in Least Squares Problems

Dean P. Foster, S. Kakade, Dean Phillips Foster, 2021, NeurIPS.

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

S. Kakade, Quanquan Gu, V. Braverman, 2022, NeurIPS.

Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression

S. Kakade, Quanquan Gu, V. Braverman, 2021, ICML.

An Improved Analysis of Training Over-parameterized Deep Neural Networks

Quanquan Gu, Difan Zou, Quanquan Gu, 2019, NeurIPS.

Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization pdf

Quanquan Gu, Difan Zou, Yuan Cao, 2021, ICLR.

Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks

Yizhou Sun, Song Jiang, Quanquan Gu, 2019, NeurIPS.

Improving Adversarial Robustness Requires Revisiting Misclassified Examples

James Bailey, Jinfeng Yi, Quanquan Gu, 2020, ICLR.

Per-Example Gradient Regularization Improves Learning Signals from Noisy Data

Difan Zou, Yuan Cao, Xuran Meng, 2023, ArXiv.

Benign Overfitting of Constant-Stepsize SGD for Linear Regression pdf

Vladimir Braverman, Sham M. Kakade, Quanquan Gu, 2021, COLT.

Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo pdf

Quanquan Gu, Difan Zou, Stanley Osher, 2019, SIAM J. Sci. Comput..

The Benefits of Mixup for Feature Learning

Quanquan Gu, Difan Zou, Yuan Cao, 2023, ICML.

Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction

Quanquan Gu, Difan Zou, Pan Xu, 2019, NeurIPS.

The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks

Quanquan Gu, Difan Zou, Yuanbin Cao, 2023, ArXiv.

A pre-registered short-term forecasting study of COVID-19 in Germany and Poland during the second wave

G. Obozinski, D. Bertsimas, Lingxiao Wang, 2021, Nature Communications.

Stochastic Variance-Reduced Hamilton Monte Carlo Methods pdf

Quanquan Gu, Pan Xu, Difan Zou, 2018, ICML.

Towards Robust Graph Incremental Learning on Evolving Graphs

Difan Zou, Zijun Zhang, Chuan Wu, 2024, ICML.

Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate

Vladimir Braverman, Quanquan Gu, Difan Zou, 2020, ICLR.

Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling pdf

Quanquan Gu, Difan Zou, Pan Xu, 2020, UAI.

Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron

S. Kakade, Quanquan Gu, V. Braverman, 2023, ICML.

Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples

S. Kakade, Quanquan Gu, V. Braverman, 2023, arXiv.org.

Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States

Michael W. Dusenberry, Benjamin D. Trump, Michael L. Mayo, 2022, Proceedings of the National Academy of Sciences of the United States of America.

Characterization on Practical Photon Counting Receiver in Optical Scattering Communication

Chen Gong, Kun Wang, Zhengyuan Xu, 2017, IEEE Transactions on Communications.

Subsampled Stochastic Variance-Reduced Gradient Langevin Dynamics

Quanquan Gu, Pan Xu, Difan Zou, 2018, UAI.

The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks

Quanquan Gu, Difan Zou, Yuan Cao, 2023, COLT.

Gradient descent optimizes over-parameterized deep ReLU networks

Quanquan Gu, Difan Zou, Yuanbin Cao, 2019, Machine Learning.

Self-training Converts Weak Learners to Strong Learners in Mixture Models pdf

Quanquan Gu, Spencer Frei, Difan Zou, 2021, AISTATS.

Direction Matters: On the Implicit Regularization Effect of Stochastic Gradient Descent with Moderate Learning Rate pdf

Vladimir Braverman, Quanquan Gu, Jingfeng Wu, 2020, ICLR.