activity
20192023
most citedR-Drop: Regularized Dropout for Neural Networks

306 citations · 332 across the 9 of their papers we have counts for

collaborators
Showing 2021Show all

7 papers · 1 filter

cs.LG2021

Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD

Bohan Wang, Huishuai Zhang, Jieyu Zhang +3

Recently, the information-theoretical framework has been proven to be able to obtain non-vacuous generalization bounds for large models trained by Stochastic Gradient Langevin Dyna…

cs.LG2021

Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit

Yichi Zhou, Shihong Song, Huishuai Zhang +3

Balancing exploration and exploitation (EE) is a fundamental problem in contex-tual bandit. One powerful principle for EE trade-off isOptimism in Face of Uncer-tainty(OFU), in whic…

cs.LG2021306 cited

R-Drop: Regularized Dropout for Neural Networks

Xiaobo Liang, Lijun Wu, Juntao Li +6

Dropout is a powerful and widely used technique to regularize the training of deep neural networks. In this paper, we introduce a simple regularization strategy upon dropout in mod…

cs.LG202114 cited

Large Scale Private Learning via Low-rank Reparametrization

Da Yu, Huishuai Zhang, Wei Chen +2

We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing indivi…

cs.LG2021

Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics

Shiqi Gong, Qi Meng, Yue Wang +4

Learning dynamics governed by differential equations is crucial for predicting and controlling the systems in science and engineering. Neural Ordinary Differential Equation (NODE),…

cs.LG2021

Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning

Da Yu, Huishuai Zhang, Wei Chen +1

The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism. However, for meaningful privacy parameters, a differentially private…