Ethan Dyer

Artificial Intelligence · 2008–2023

A researcher in the Science corpus: 13 papers; trusts 545 researchers and is trusted by 33 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 380 citations into it; #7,164 of 35,345 by trust here, #2,798 by citations
• Computer Vision and Pattern Recognition — 175 citations into it; #11,109 of 21,575 by trust here, #10,500 by citations
• Scaling & Learning Theory — 72 citations into it; #133 of 428 by trust here, #200 by citations
• Optimization & Training — 71 citations into it; #1,793 of 2,601 by trust here, #1,280 by citations
• Evaluation & Benchmarks — 62 citations into it
• Safety, Robustness & Interpretability — 47 citations into it; #1,169 of 2,251 by trust here, #1,731 by citations
• Model Architectures — 42 citations into it
• Statistical and Nonlinear Physics — 33 citations into it; #6,963 of 10,127 by trust here, #7,402 by citations

Whom Ethan Dyer trusts overall

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

1. Geoffrey E. Hinton
2. Alex Krizhevsky
3. Kaiming He
4. Yoshua Bengio
5. Diederik P. Kingma
6. Yann LeCun
7. Ilya Sutskever
8. Radford M. Neal
9. Jeffrey Pennington
10. Karen Simonyan

Who trusts Ethan Dyer overall

1. Kurt Hinterbichler
2. Boris Hanin
3. Yasaman Bahri
4. Timothy Nguyen
5. Mario Geiger
6. Aitor Lewkowycz
7. Roman Novak
8. Mihai Nica
9. Timothée Lesort
10. Jaehoon Lee

Papers from Ethan Dyer's perspective

Ordered by how strongly the researchers Ethan Dyer 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. Gradient-based learning applied to document recognition
6. Long Short-Term Memory
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

• Solving Quantitative Reasoning Problems with Language Models (2022) — 1,845 citations
• PaLM 2 Technical Report (2023) — 1,524 citations
• Explaining neural scaling laws (2021) — 491 citations
• The large learning rate phase of deep learning: the catapult mechanism (2020) — 292 citations
• Gradient Descent Happens in a Tiny Subspace (2018) — 304 citations
• Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics (2020) — 216 citations
• Affinity and Diversity: Quantifying Mechanisms of Data Augmentation (2020) — 87 citations
• Asymptotics of Wide Networks from Feynman Diagrams (2019) — 127 citations
• Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models (2023) — 337 citations
• Effect of scale on catastrophic forgetting in neural networks (2022) — 226 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
• Tradeoffs in Data Augmentation: An Empirical Study (2021) — 72 citations
• Boundary Terms, Variational Principles and Higher Derivative Modified Gravity (2008) — 196 citations