Lili Su

Artificial Intelligence · 2016–2020

A researcher in the Science corpus: 10 papers; trusts 108 researchers and is trusted by 54 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 93 citations into it; #3,342 of 35,345 by trust here, #6,378 by citations
• Statistics and Probability — 51 citations into it
• Optimization & Training — 43 citations into it; #669 of 2,601 by trust here, #1,009 by citations
• Computer Networks and Communications — 31 citations into it; #817 of 9,886 by trust here, #1,955 by citations
• Statistical Learning Theory — 30 citations into it
• Computational Mechanics — 27 citations into it
• Safety, Robustness & Interpretability — 17 citations into it; #1,034 of 2,251 by trust here, #2,110 by citations
• Statistical and Nonlinear Physics — 15 citations into it

Whom Lili Su trusts overall

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

1. Yuanzhi Li
2. Dimitri P. Bertsekas
3. Yudong Chen
4. John N. Tsitsiklis
5. Ali Jadbabaie
6. Seif Haridi
7. Terence Tao
8. Jacob Steinhardt
9. John C. Duchi
10. Zeyuan Allen-Zhu

Who trusts Lili Su overall

1. Cong Xie
2. Oluwasanmi Koyejo
3. El Mahdi El Mhamdi
4. Dong Yin
5. Indranil Gupta
6. Rachid Guerraoui
7. Yudong Chen
8. Deepesh Data
9. Peva Blanchard
10. Lingjuan Lyu

Papers from Lili Su's perspective

Ordered by how strongly the researchers Lili Su trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
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. Attention is All you Need (Neural Information Processing Systems)
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

• Distributed Statistical Machine Learning in Adversarial Settings (2017) — 293 citations
• Securing Distributed Machine Learning in High Dimensions (2018) — 37 citations
• Defending Distributed Systems Against Adversarial Attacks: Consensus, Consensusbased Learning, and Statistical Learning (2020) — 14 citations
• On Learning Over-parameterized Neural Networks: A Functional Approximation Prospective (2019) — 62 citations
• Securing Distributed Gradient Descent in High Dimensional Statistical Learning (2018) — 65 citations
• Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent (2017) — 599 citations
• Robust Multi-agent Optimization: Coping with Byzantine Agents with Input Redundancy (2016) — 13 citations
• Non-Bayesian Learning in the Presence of Byzantine Agents (2016) — 39 citations
• Defending non-Bayesian learning against adversarial attacks (2016) — 54 citations
• Fault-Tolerant Multi-Agent Optimization: Optimal Iterative Distributed Algorithms (2016) — 152 citations