Name
Affiliation
Papers
ZHEWEI YAO
Department of Mathematics, Zhiyuan College, Shanghai Jiao Tong University, Shanghai 200240, China
29
Collaborators
Citations 
PageRank 
67
31
10.58
Referers 
Referees 
References 
188
340
109
Search Limit
100340
Title
Citations
PageRank
Year
How Much Can CLIP Benefit Vision-and-Language Tasks?00.342022
Integer-Only Zero-Shot Quantization for Efficient Speech Recognition00.342022
I-Bert: Integer-Only Bert Quantization00.342021
Adahessian: An Adaptive Second Order Optimizer For Machine Learning00.342021
What's Hidden in a One-layer Randomly Weighted Transformer?00.342021
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models.00.342021
HAWQ-V3: Dyadic Neural Network Quantization00.342021
Actnn: Reducing Training Memory Footprint Via 2-Bit Activation Compressed Training00.342021
HAWQ-V2 - Hessian Aware trace-Weighted Quantization of Neural Networks.00.342020
Q-Bert: Hessian Based Ultra Low Precision Quantization Of Bert10.342020
PowerNorm - Rethinking Batch Normalization in Transformers.00.342020
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks00.342020
MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding.10.392020
PyHessian: Neural Networks Through the Lens of the Hessian20.372020
ZeroQ: A Novel Zero Shot Quantization Framework30.382020
ANODEV2: A Coupled Neural ODE Evolution Framework.00.342019
ANODEV2: A Coupled Neural ODE Framework.00.342019
Residual Networks as Nonlinear Systems: Stability Analysis using Linearization.00.342019
Shallow Learning for Fluid Flow Reconstruction with Limited Sensors and Limited Data.00.342019
Jumprelu: A Retrofit Defense Strategy For Adversarial Attacks00.342019
Inefficiency Of K-Fac For Large Batch Size Training00.342019
HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision120.612019
Parameter Re-Initialization through Cyclical Batch Size Schedules.00.342018
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries.60.422018
On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent.20.362018
Large batch size training of neural networks with adversarial training and second-order information.10.382018
Trust Region Based Adversarial Attack On Neural Networks00.342018
On an adaptive preconditioned Crank-Nicolson MCMC algorithm for infinite dimensional Bayesian inference.30.572017
A Hybrid Adaptive MCMC Algorithm in Function Spaces00.342017