Lechao Xiao

Artificial Intelligence · 2018–2023

A researcher in the Science corpus: 8 papers; trusts 179 researchers and is trusted by 31 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 216 citations into it; #7,690 of 35,345 by trust here, #4,205 by citations
• Computer Vision and Pattern Recognition — 102 citations into it; #6,253 of 21,575 by trust here, #6,146 by citations
• Scaling & Learning Theory — 93 citations into it; #116 of 428 by trust here, #80 by citations
• Optimization & Training — 80 citations into it; #1,229 of 2,601 by trust here, #1,034 by citations
• Model Architectures — 65 citations into it; #1,740 of 2,278 by trust here, #1,693 by citations
• Statistical and Nonlinear Physics — 50 citations into it; #7,299 of 10,127 by trust here, #4,281 by citations
• Statistical Learning Theory — 39 citations into it
• Probabilistic & Bayesian Methods — 29 citations into it; #1,286 of 1,525 by trust here, #648 by citations

Whom Lechao Xiao trusts overall

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

1. Alex Krizhevsky
2. Greg Yang
3. Sam Schoenholz
4. Geoffrey E. Hinton
5. Kaiming He
6. Yoshua Bengio
7. Yann LeCun
8. Diederik P. Kingma
9. Roman Novak
10. Ilya Sutskever

Who trusts Lechao Xiao overall

1. Greg Yang
2. Roman Novak
3. Timothy Nguyen
4. Jaehoon Lee
5. Sam Schoenholz
6. Yann Dauphin
7. Soufiane Hayou
8. Jeffrey Pennington
9. Jascha Narain Sohl-Dickstein
10. Yasaman Bahri

Papers from Lechao Xiao's perspective

Ordered by how strongly the researchers Lechao Xiao 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. Gradient-based learning applied to document recognition
5. Attention is All you Need (Neural Information Processing Systems)
6. Long Short-Term Memory
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Wide neural networks of any depth evolve as linear models under gradient descent (2019) — 1,337 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
• Dataset Distillation with Infinitely Wide Convolutional Networks (2021) — 307 citations
• Neural Tangents: Fast and Easy Infinite Neural Networks in Python (2019) — 261 citations
• Disentangling trainability and generalization in deep learning (2019) — 35 citations
• The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks (2020) — 74 citations
• Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models (2023) — 337 citations