Tengyuan Liang

Artificial Intelligence · 2015–2020

A researcher in the Science corpus: 9 papers; trusts 303 researchers and is trusted by 52 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 117 citations into it; #4,180 of 35,345 by trust here, #8,077 by citations
• Statistics and Probability — 104 citations into it; #2,366 of 12,932 by trust here, #2,751 by citations
• Computer Vision and Pattern Recognition — 50 citations into it; #20,498 of 21,575 by trust here, #20,271 by citations
• Statistical Learning Theory — 39 citations into it; #1,011 of 1,038 by trust here, #874 by citations
• Generative Models — 34 citations into it; #596 of 1,956 by trust here, #1,382 by citations
• Scaling & Learning Theory — 33 citations into it; #129 of 428 by trust here, #275 by citations
• Computational Mechanics — 27 citations into it; #6,391 of 10,001 by trust here, #7,884 by citations
• Causal Inference & Discovery — 24 citations into it; #237 of 364 by trust here, #266 by citations

Whom Tengyuan Liang trusts overall

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

1. Shahar Mendelson
2. Peter L. Bartlett
3. Diederik P. Kingma
4. Dmitry Yarotsky
5. Individualized Treat
6. Alexandre B. Tsybakov
7. Vladimir Koltchinskii
8. Francis R. Bach
9. Geoffrey E. Hinton
10. L. Eon Bottou

Who trusts Tengyuan Liang overall

1. Max H. Farrell
2. Waïss Azizian
3. Yu-Guan Hsieh
4. Gauthier Gidel
5. Sharan Vaswani
6. Simon Lacoste-Julien
7. Sanjog Misra
8. Abdulkadir Canatar
9. Ioannis Mitliagkas
10. Colin Wei

Papers from Tengyuan Liang's perspective

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

Their papers

• Just Interpolate: Kernel "Ridgeless" Regression Can Generalize (2018) — 379 citations
• Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks (2018) — 226 citations
• Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits (2019) — 42 citations
• Deep Neural Networks for Estimation and Inference: Application to Causal Effects and Other Semiparametric Estimands (2018) — 269 citations
• Learning with Square Loss: Localization through Offset Rademacher Complexity (2015) — 85 citations
• DEEP NEURAL NETWORKS FOR ESTIMATION AND INFERENCE (2020)
• On the Risk of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels (2019) — 29 citations
• On How Well Generative Adversarial Networks Learn Densities: Nonparametric and Parametric Results (2018) — 47 citations
• How Well Can Generative Adversarial Networks (GAN) Learn Densities: A Nonparametric View (2017) — 43 citations