Simon Shaolei Du
Artificial Intelligence · 2017–2021
A researcher in the Science corpus: 27 papers; trusts 1,223 researchers and is trusted by 511 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 721 citations into it; #1,401 of 36,961 by trust here, #1,442 by citations
- Optimization & Training — 229 citations into it; #314 of 2,605 by trust here, #253 by citations
- Computer Vision and Pattern Recognition — 202 citations into it; #3,542 of 21,973 by trust here, #2,077 by citations
- Reinforcement Learning — 153 citations into it
- Scaling & Learning Theory — 147 citations into it; #88 of 429 by trust here, #85 by citations
- Statistical Learning Theory — 136 citations into it; #633 of 1,040 by trust here, #319 by citations
- Computational Mechanics — 135 citations into it; #1,167 of 10,021 by trust here, #478 by citations
- Management Science and Operations Research — 96 citations into it; #6,171 of 12,201 by trust here, #4,447 by citations
Whom Simon Shaolei Du trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Jason D. Lee
- Kaiming He
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Richard S. Sutton
- Diederik P. Kingma
- Yann LeCun
- Rong Ge
- Sham M. Kakade
Who trusts Simon Shaolei Du overall
- Sanjeev Arora
- Jason D. Lee
- Difan Zou
- Wei Hu
- Yuanzhi Li
- Quanquan Gu
- Ruosong Wang
- Zeyuan Allen-Zhu
- Samet Oymak
- Colin Wei
Papers from Simon Shaolei Du's perspective
Ordered by how strongly the researchers Simon Shaolei Du 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Gradient Descent Provably Optimizes Over-parameterized Neural Networks (2018) — 1,387 citations
- Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks (2019) — 1,081 citations
- Gradient Descent Finds Global Minima of Deep Neural Networks (2018) — 1,268 citations
- On Exact Computation with an Infinitely Wide Neural Net (2019) — 1,059 citations
- Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced (2018) — 284 citations
- Provably efficient RL with Rich Observations via Latent State Decoding (2019) — 254 citations
- Stochastic Variance Reduction Methods for Policy Evaluation (2017) — 170 citations
- On the Power of Over-parametrization in Neural Networks with Quadratic Activation (2018) — 293 citations
- Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? (2019) — 215 citations
- Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima (2017) — 243 citations
- Few-Shot Learning via Learning the Representation, Provably (2020) — 298 citations
- Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks (2019) — 171 citations
- Enhanced Convolutional Neural Tangent Kernels (2019) — 138 citations
- When is a Convolutional Filter Easy To Learn? (2017) — 131 citations
- Width Provably Matters in Optimization for Deep Linear Neural Networks (2019) — 104 citations
- How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks (2020) — 370 citations
- Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network (2019) — 68 citations
- Provable Representation Learning for Imitation Learning via Bi-level Optimization (2020) — 65 citations
- Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality (2020) — 56 citations
- On Reward-Free Reinforcement Learning with Linear Function Approximation (2020) — 119 citations