A bibliometric analysis of autism spectrum disorder signaling pathways research in the past decade von Lyu, Kaifeng, Li, Jiangshan, Chen, Min, Li, Wu, Zhang, Wei, Hu, Meichao, Zhang, Yuxing, Feng, Xiang

Volltext

Effect of COVID-19 on autism spectrum disorders: A bibliometric analysis based on original articles von Lyu, Kaifeng, Li, Jiang-shan, Chen, Min, Zhang, Wei, Hu, Meichao

Volltext

RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval von Wen, Kaiyue, Dang, Xingyu, Lyu, Kaifeng

Volltext bestellen

Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction von Lyu, Kaifeng, Li, Zhiyuan, Arora, Sanjeev

Volltext bestellen

A Quadratic Synchronization Rule for Distributed Deep Learning von Gu, Xinran, Lyu, Kaifeng, Arora, Sanjeev, Zhang, Jingzhao, Huang, Longbo

Volltext bestellen

The Marginal Value of Momentum for Small Learning Rate SGD von Wang, Runzhe, Malladi, Sadhika, Wang, Tianhao, Lyu, Kaifeng, Li, Zhiyuan

Volltext bestellen

New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound von Gupta, Arushi, Saunshi, Nikunj, Yu, Dingli, Lyu, Kaifeng, Arora, Sanjeev

Volltext bestellen

Safety Alignment Should Be Made More Than Just a Few Tokens Deep von Qi, Xiangyu, Panda, Ashwinee, Lyu, Kaifeng, Ma, Xiao, Roy, Subhrajit, Beirami, Ahmad, Mittal, Prateek, Henderson, Peter

Volltext bestellen

RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval von Wen, Kaiyue, Dang, Xingyu, Lyu, Kaifeng

Volltext

Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate von Li, Zhiyuan, Lyu, Kaifeng, Arora, Sanjeev

Volltext bestellen

Efficient Stagewise Pretraining via Progressive Subnetworks von Panigrahi, Abhishek, Saunshi, Nikunj, Lyu, Kaifeng, Miryoosefi, Sobhan, Reddi, Sashank, Kale, Satyen, Kumar, Sanjiv

Volltext bestellen

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking von Lyu, Kaifeng, Jin, Jikai, Li, Zhiyuan, Du, Simon S, Lee, Jason D, Hu, Wei

Volltext bestellen

Gradient Descent Maximizes the Margin of Homogeneous Neural Networks von Lyu, Kaifeng, Li, Jian

Volltext

AI-Assisted Generation of Difficult Math Questions von Shah, Vedant, Yu, Dingli, Lyu, Kaifeng, Park, Simon, Yu, Jiatong, He, Yinghui, Ke, Nan Rosemary, Mozer, Michael, Bengio, Yoshua, Arora, Sanjeev, Goyal, Anirudh

Volltext bestellen

On the SDEs and Scaling Rules for Adaptive Gradient Algorithms von Malladi, Sadhika, Lyu, Kaifeng, Panigrahi, Abhishek, Arora, Sanjeev

Volltext

Theoretical Analysis of Auto Rate-Tuning by Batch Normalization von Arora, Sanjeev, Li, Zhiyuan, Lyu, Kaifeng

Volltext bestellen

The Marginal Value of Momentum for Small Learning Rate SGD von Wang, Runzhe, Malladi, Sadhika, Wang, Tianhao, Lyu, Kaifeng, Li, Zhiyuan

Volltext

A Quadratic Synchronization Rule for Distributed Deep Learning von Gu, Xinran, Lyu, Kaifeng, Arora, Sanjeev, Zhang, Jingzhao, Huang, Longbo

Volltext

Why (and When) does Local SGD Generalize Better than SGD? von Gu, Xinran, Lyu, Kaifeng, Huang, Longbo, Arora, Sanjeev

Volltext

New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound von Gupta, Arushi, Saunshi, Nikunj, Yu, Dingli, Lyu, Kaifeng, Arora, Sanjeev

Volltext