Xiyu Zhai

Artificial Intelligence · 2017–2019

A researcher in the Science corpus: 4 papers; trusts 50 researchers and is trusted by 72 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 88 citations into it; #2,879 of 35,345 by trust here, #3,175 by citations
• Optimization & Training — 43 citations into it; #374 of 2,601 by trust here, #331 by citations
• Scaling & Learning Theory — 35 citations into it
• Computer Vision and Pattern Recognition — 27 citations into it; #4,370 of 21,575 by trust here, #4,212 by citations
• Computational Mechanics — 25 citations into it; #2,073 of 10,001 by trust here, #701 by citations
• Statistical Learning Theory — 23 citations into it
• Statistics and Probability — 22 citations into it; #9,529 of 12,932 by trust here, #7,508 by citations
• Model Architectures — 16 citations into it; #897 of 2,278 by trust here, #625 by citations

Whom Xiyu Zhai trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Simon Shaolei Du
2. Moritz Hardt
3. Itay Safran
4. Jason D. Lee
5. Yuanzhi Li
6. David A. McAllester
7. Rong Ge
8. Geoffrey E. Hinton
9. Kaiming He
10. Alex Krizhevsky

Who trusts Xiyu Zhai overall

1. Simon Shaolei Du
2. Difan Zou
3. Sanjeev Arora
4. Reinhard Heckel
5. Yuanzhi Li
6. Samet Oymak
7. Quanquan Gu
8. Zeyuan Allen-Zhu
9. Atsushi Nitanda
10. M. Soltanolkotabi

Papers from Xiyu Zhai's perspective

Ordered by how strongly the researchers Xiyu Zhai trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. Learning Multiple Layers of Features from Tiny Images
8. ImageNet: A large-scale hierarchical image database
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Gradient Descent Provably Optimizes Over-parameterized Neural Networks (2018) — 1,387 citations
• Gradient Descent Finds Global Minima of Deep Neural Networks (2018) — 1,268 citations
• Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints (2017) — 177 citations
• On the Risk of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels (2019) — 29 citations