Song Mei
Artificial Intelligence · with Montanari · 2016–2023
A researcher in the Science corpus: 10 papers; trusts 118 researchers and is trusted by 103 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 192 citations into it; #3,043 of 36,961 by trust here, #4,325 by citations
- Optimization & Training — 75 citations into it; #1,557 of 2,605 by trust here, #1,337 by citations
- Statistical Learning Theory — 67 citations into it; #469 of 1,040 by trust here, #317 by citations
- Scaling & Learning Theory — 66 citations into it; #106 of 429 by trust here, #216 by citations
- Statistics and Probability — 55 citations into it; #753 of 13,188 by trust here, #698 by citations
- Computer Vision and Pattern Recognition — 54 citations into it
- Computational Mechanics — 42 citations into it; #5,335 of 10,021 by trust here, #3,478 by citations
- Model Architectures — 36 citations into it; #350 of 2,288 by trust here, #572 by citations
Whom Song Mei trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Francis R. Bach
- Peter L. Bartlett
- Lénaïc Chizat
- Yann LeCun
- Mikhail Belkin
- Yoshua Bengio
- Roman Vershynin
- Geoffrey E. Hinton
- Alex Krizhevsky
- Michel Ledoux
Who trusts Song Mei overall
- Lénaïc Chizat
- Alberto Bietti
- Samet Oymak
- Jason D. Lee
- Charles H. Martin
- Cong Fang
- Francis R. Bach
- Jimmy Ba
- Taiji Suzuki
- Behrooz Ghorbani
Papers from Song Mei's perspective
Ordered by how strongly the researchers Song Mei 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
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- 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
- The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve (2019) — 722 citations
- A mean field view of the landscape of two-layer neural networks (2018) — 1,021 citations
- Linearized two-layers neural networks in high dimension (2019) — 274 citations
- Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit (2019) — 328 citations
- The landscape of empirical risk for nonconvex losses (2016) — 333 citations
- Discussion of: “Nonparametric regression using deep neural networks with ReLU activation function” (2020) — 27 citations
- Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection (2023) — 340 citations
- When do neural networks outperform kernel methods? (2020) — 214 citations
- Limitations of Lazy Training of Two-layers Neural Networks (2019) — 152 citations
- The Landscape of the Spiked Tensor Model (2017) — 142 citations