Colin Wei

Artificial Intelligence · 2016–2024

A researcher in the Science corpus: 12 papers; trusts 795 researchers and is trusted by 41 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 341 citations into it; #5,513 of 35,345 by trust here, #5,187 by citations
• Computer Vision and Pattern Recognition — 213 citations into it; #8,973 of 21,575 by trust here, #7,249 by citations
• Optimization & Training — 127 citations into it; #995 of 2,601 by trust here, #672 by citations
• Scaling & Learning Theory — 113 citations into it; #320 of 428 by trust here, #362 by citations
• Statistical Learning Theory — 72 citations into it; #618 of 1,038 by trust here, #459 by citations
• Computational Mechanics — 59 citations into it; #3,208 of 10,001 by trust here, #6,582 by citations
• Representation & Self-Supervised Learning — 56 citations into it
• Model Architectures — 36 citations into it

Whom Colin Wei trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Diederik P. Kingma
5. Behnam Neyshabur
6. Yann LeCun
7. Kaiming He
8. Ilya Sutskever
9. Peter L. Bartlett
10. Karen Simonyan

Who trusts Colin Wei overall

1. Tengyu Ma
2. Yu Bai
3. Jason D. Lee
4. Sanjeev Arora
5. Sham M. Kakade
6. Yuanzhi Li
7. Simon Shaolei Du
8. Kaifeng Lyu
9. Boris Hanin
10. Niladri S. Chatterji

Papers from Colin Wei's perspective

Ordered by how strongly the researchers Colin Wei 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. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Generic 3D Representation via Pose Estimation and Matching (2016) — 98 citations
• Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss (2019) — 2,156 citations
• Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin (2019) — 95 citations
• Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks (2019) — 341 citations
• Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel (2018) — 275 citations
• The Implicit and Explicit Regularization Effects of Dropout (2020) — 130 citations
• Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss (2021) — 402 citations
• Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation (2019) — 128 citations
• GPT-4o System Card (2024) — 4,622 citations
• Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning (2021) — 119 citations
• Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective (2020)
• On the Margin Theory of Feedforward Neural Networks (2018) — 96 citations