Greg Yang
Artificial Intelligence · 2016–2022
A researcher in the Science corpus: 17 papers; trusts 1,723 researchers and is trusted by 252 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 500 citations into it; #1,981 of 36,961 by trust here, #3,563 by citations
- Computer Vision and Pattern Recognition — 214 citations into it; #3,744 of 21,973 by trust here, #4,657 by citations
- Model Architectures — 153 citations into it; #594 of 2,288 by trust here, #1,063 by citations
- Optimization & Training — 123 citations into it; #1,112 of 2,605 by trust here, #988 by citations
- Scaling & Learning Theory — 120 citations into it; #41 of 429 by trust here, #101 by citations
- Statistical and Nonlinear Physics — 95 citations into it; #1,580 of 10,175 by trust here, #2,398 by citations
- Safety, Robustness & Interpretability — 64 citations into it
- Statistical Learning Theory — 61 citations into it; #355 of 1,040 by trust here, #532 by citations
Whom Greg Yang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Jeffrey Pennington
- Yoshua Bengio
- Kaiming He
- Sam Schoenholz
- Ilya Sutskever
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yann LeCun
- Diederik P. Kingma
- Alex Graves
Who trusts Greg Yang overall
- Soufiane Hayou
- Lechao Xiao
- J. Edward Hu
- Zeyuan Allen-Zhu
- Ryo Karakida
- Boris Hanin
- Sam Schoenholz
- Jeffrey Pennington
- Yuanzhi Li
- Roman Novak
Papers from Greg Yang's perspective
Ordered by how strongly the researchers Greg Yang trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes (2018) — 331 citations
- Mean Field Residual Networks: On the Edge of Chaos (2017) — 219 citations
- Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers (2019) — 640 citations
- A Fine-Grained Spectral Perspective on Neural Networks (2019) — 122 citations
- Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation (2019) — 313 citations
- NAIL: A General Interactive Fiction Agent (2019) — 39 citations
- Lie Access Neural Turing Machine (2016) — 17 citations
- Deep Mean Field Theory: Layerwise Variance and Width Variation as Methods to Control Gradient Explosion (2018) — 24 citations
- Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs (2019) — 44 citations
- Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes (2019) — 243 citations
- Tensor Programs III: Neural Matrix Laws (2020) — 64 citations
- A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks (2019) — 299 citations
- Feature Learning in Infinite-Width Neural Networks (2020) — 209 citations
- Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer (2022) — 295 citations
- Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics (2021) — 81 citations
- Tensor Programs II: Neural Tangent Kernel for Any Architecture (2020) — 176 citations
- A Mean Field Theory of Batch Normalization (2019) — 192 citations