Zhao Song
Artificial Intelligence · with Dhillon · 2014–2018
A researcher in the Science corpus: 10 papers; trusts 369 researchers and is trusted by 87 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 248 citations into it; #3,328 of 36,961 by trust here, #3,364 by citations
- Computer Vision and Pattern Recognition — 73 citations into it; #6,233 of 21,973 by trust here, #10,433 by citations
- Optimization & Training — 70 citations into it; #403 of 2,605 by trust here, #436 by citations
- Computational Theory and Mathematics — 66 citations into it; #10,052 of 12,489 by trust here, #7,741 by citations
- Computational Mechanics — 58 citations into it; #8,047 of 10,021 by trust here, #6,893 by citations
- Model Architectures — 50 citations into it; #1,412 of 2,288 by trust here, #1,932 by citations
- Statistical Learning Theory — 43 citations into it; #511 of 1,040 by trust here, #331 by citations
- Scaling & Learning Theory — 40 citations into it; #73 of 429 by trust here, #104 by citations
Whom Zhao Song trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kenneth L. Clarkson
- Sanjeev Arora
- Geoffrey E. Hinton
- Yoshua Bengio
- David P. Woodruff
- Alex Krizhevsky
- Diederik P. Kingma
- Ilya Sutskever
- Yann LeCun
- Kaiming He
Who trusts Zhao Song overall
- Zeyuan Allen-Zhu
- Simon Shaolei Du
- Yuanzhi Li
- Samet Oymak
- Difan Zou
- Jason D. Lee
- Quanquan Gu
- M. Soltanolkotabi
- Greg Yang
- Lili Su
Papers from Zhao Song's perspective
Ordered by how strongly the researchers Zhao Song trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- 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
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- A Convergence Theory for Deep Learning via Over-Parameterization (2018) — 1,651 citations
- Towards Fast Computation of Certified Robustness for ReLU Networks (2018) — 755 citations
- Recovery Guarantees for One-hidden-layer Neural Networks (2017) — 349 citations
- On the Convergence Rate of Training Recurrent Neural Networks (2018) — 205 citations
- Learning Long Term Dependencies via Fourier Recurrent Units (2018) — 45 citations
- Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels (2017) — 75 citations
- Weighted low rank approximations with provable guarantees (2016) — 110 citations
- Solving linear programs in the current matrix multiplication time (2018) — 376 citations
- Low rank approximation with entrywise l1-norm error (2017) — 107 citations
- Batch codes through dense graphs without short cycles (2014) — 53 citations