Eran Malach

Artificial Intelligence · 2017–2020

A researcher in the Science corpus: 4 papers; trusts 150 researchers and is trusted by 44 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 65 citations into it; #5,169 of 35,345 by trust here, #7,531 by citations
• Computer Vision and Pattern Recognition — 36 citations into it; #5,549 of 21,575 by trust here, #10,500 by citations
• Optimization & Training — 23 citations into it; #1,706 of 2,601 by trust here, #1,195 by citations
• Scaling & Learning Theory — 18 citations into it
• Statistical Learning Theory — 17 citations into it; #529 of 1,038 by trust here, #396 by citations
• Efficiency & Compression — 13 citations into it
• Model Architectures — 9 citations into it
• Statistical and Nonlinear Physics — 6 citations into it

Whom Eran Malach trusts overall

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

1. Yoshua Bengio
2. Diederik P. Kingma
3. Geoffrey E. Hinton
4. Yves Grandvalet
5. Shai Shalev-Shwartz
6. Alex Krizhevsky
7. Yann LeCun
8. Jimmy Ba
9. Kaiming He
10. Ilya Sutskever

Who trusts Eran Malach overall

1. Zeyuan Allen-Zhu
2. Hwanjun Song
3. Bo Han
4. Arild Nøkland
5. Yuanzhi Li
6. Pengfei Chen
7. Devraj Mandal
8. Xingrui Yu
9. Xiaobo Xia
10. Steven Euijong Whang

Papers from Eran Malach's perspective

Ordered by how strongly the researchers Eran Malach 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. Going deeper with convolutions

Their papers

• SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data (2017) — 287 citations
• Decoupling "when to update" from "how to update" (2017) — 655 citations
• Proving the Lottery Ticket Hypothesis: Pruning is All You Need (2020) — 335 citations
• A Provably Correct Algorithm for Deep Learning that Actually Works (2018) — 39 citations