Xiang Li

Artificial Intelligence · with Wang · 2019

A researcher in the Science corpus: 4 papers; trusts 100 researchers and is trusted by 9 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 130 citations into it; #16,413 of 35,345 by trust here, #7,945 by citations
• Optimization & Training — 116 citations into it
• Federated & Distributed Learning — 59 citations into it; #129 of 319 by trust here, #76 by citations
• Computational Mechanics — 42 citations into it
• Computer Networks and Communications — 32 citations into it; #3,942 of 9,886 by trust here, #1,003 by citations
• Computer Vision and Pattern Recognition — 31 citations into it
• ML Systems & Hardware — 24 citations into it
• Computational Theory and Mathematics — 19 citations into it

Whom Xiang Li trusts overall

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

1. Yuchen Zhang
2. Shusen Wang
3. Michael W. Mahoney
4. Yurii E. Nesterov
5. Ohad Shamir
6. Sebastian U. Stich
7. Jianyu Wang
8. L. Eon Bottou
9. John C. Duchi
10. Jason D. Lee

Who trusts Xiang Li overall

1. Yae Jee Cho
2. Tian Li
3. Farzin Haddadpour
4. Jianyu Wang
5. John Nguyen
6. Deepesh Data
7. Zachary B. Charles
8. Young Geun Kim
9. Hong-You Chen
10. Canh T. Dinh

Papers from Xiang Li's perspective

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

Their papers

• On the Convergence of FedAvg on Non-IID Data (2019) — 3,042 citations
• Communication Efficient Decentralized Training with Multiple Local Updates (2019) — 56 citations
• Do Subsampled Newton Methods Work for High-Dimensional Data? (2019) — 16 citations
• Communication-Efficient Local Decentralized SGD Methods (2019) — 76 citations