Hongyang Zhang

Artificial Intelligence · 8 papers · 2017–2020

A researcher in the Science corpus: 8 papers; trusts 377 researchers and is trusted by 31 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 255 citations into it; #9,550 of 35,345 by trust here, #5,533 by citations
• Computer Vision and Pattern Recognition — 121 citations into it
• Safety, Robustness & Interpretability — 91 citations into it; #964 of 2,251 by trust here, #522 by citations
• Optimization & Training — 84 citations into it; #1,556 of 2,601 by trust here, #1,942 by citations
• Scaling & Learning Theory — 50 citations into it; #173 of 428 by trust here, #241 by citations
• Computational Mechanics — 45 citations into it; #4,804 of 10,001 by trust here, #5,567 by citations
• Statistical Learning Theory — 40 citations into it; #375 of 1,038 by trust here, #334 by citations
• Model Architectures — 34 citations into it

Whom Hongyang Zhang trusts overall

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

1. Alex Krizhevsky
2. Kaiming He
3. Yann LeCun
4. Geoffrey E. Hinton
5. Yoshua Bengio
6. Karen Simonyan
7. Diederik P. Kingma
8. Ilya Sutskever
9. Christian Szegedy
10. Ian J. Goodfellow

Who trusts Hongyang Zhang overall

1. Francesco Croce
2. Sven Gowal
3. Tianyu Pang
4. Matthias Hein
5. Micah Goldblum
6. Tianyuan Zhang
7. Sylvestre-Alvise Rebuffi
8. Tianlong Chen
9. Aditi Raghunathan
10. Huan Zhang

Papers from Hongyang Zhang's perspective

Ordered by how strongly the researchers Hongyang Zhang 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. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Going deeper with convolutions

Their papers

• Theoretically Principled Trade-off between Robustness and Accuracy (2019) — 3,092 citations
• Algorithmic Regularization in Over-parameterized Matrix Recovery (2017) — 31 citations
• On the Generalization Effects of Linear Transformations in Data Augmentation (2020) — 93 citations
• A Closer Look at Accuracy vs. Robustness (2020) — 328 citations
• Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK (2020) — 29 citations
• Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex (2018) — 14 citations
• Differentially Private Clustering in High-Dimensional Euclidean Spaces (2017) — 92 citations
• Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations (2017) — 328 citations