Yasaman Bahri

Artificial Intelligence · 2017–2024

A researcher in the Science corpus: 13 papers; trusts 275 researchers and is trusted by 63 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 229 citations into it; #4,534 of 35,345 by trust here, #2,561 by citations
• Computer Vision and Pattern Recognition — 120 citations into it; #9,293 of 21,575 by trust here, #6,795 by citations
• Optimization & Training — 94 citations into it; #1,240 of 2,601 by trust here, #954 by citations
• Scaling & Learning Theory — 91 citations into it; #76 of 428 by trust here, #63 by citations
• Model Architectures — 62 citations into it; #983 of 2,278 by trust here, #794 by citations
• Probabilistic & Bayesian Methods — 43 citations into it; #605 of 1,525 by trust here, #244 by citations
• Statistical and Nonlinear Physics — 41 citations into it; #3,058 of 10,127 by trust here, #976 by citations
• Statistical Learning Theory — 31 citations into it

Whom Yasaman Bahri trusts overall

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

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

Who trusts Yasaman Bahri overall

1. Greg Yang
2. Lechao Xiao
3. Roman Novak
4. Zeyuan Allen-Zhu
5. Ryo Karakida
6. Soufiane Hayou
7. Daniel S. Park
8. Jeffrey Pennington
9. Timothy Nguyen
10. Jaehoon Lee

Papers from Yasaman Bahri's perspective

Ordered by how strongly the researchers Yasaman Bahri 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. Learning Multiple Layers of Features from Tiny Images
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

• Wide neural networks of any depth evolve as linear models under gradient descent (2019) — 1,337 citations
• Deep Neural Networks as Gaussian Processes (2017) — 1,255 citations
• Sensitivity and Generalization in Neural Networks: an Empirical Study (2018) — 514 citations
• Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks (2018) — 392 citations
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes (2018) — 331 citations
• Explaining neural scaling laws (2021) — 491 citations
• The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning (2021) — 94 citations
• The large learning rate phase of deep learning: the catapult mechanism (2020) — 292 citations
• Statistical mechanics of deep learning (2024) — 234 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2023) — 266 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
• Statistical Mechanics of Deep Learning (2020) — 53 citations
• Geometry of Neural Network Loss Surfaces via Random Matrix Theory (2017) — 169 citations