Demjan Grubic

Optimization & Training · 2016–2017

A researcher in the Science corpus: 3 papers; trusts 47 researchers and is trusted by 26 researchers here, as inferred from the citation graph.

Subfields

• Optimization & Training — 38 citations into it; #753 of 2,601 by trust here, #495 by citations
• Artificial Intelligence — 35 citations into it; #17,414 of 35,345 by trust here, #12,083 by citations
• Computer Vision and Pattern Recognition — 20 citations into it; #12,604 of 21,575 by trust here, #8,409 by citations
• Computational Mechanics — 11 citations into it
• Model Architectures — 10 citations into it
• ML Systems & Hardware — 7 citations into it
• Computational Theory and Mathematics — 5 citations into it

Whom Demjan Grubic trusts overall

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

1. Alex Krizhevsky
2. Yann LeCun
3. Geoffrey E. Hinton
4. Karen Simonyan
5. Sergey Ioffe
6. Sepp Hochreiter
7. Ilya Sutskever
8. Sébastien Bubeck
9. Nikko Ström
10. Kaiming He

Who trusts Demjan Grubic overall

1. Sebastian U. Stich
2. Ahmed Khaled
3. Peter Richtárik
4. Konstantin Mishchenko
5. Amirhossein Reisizadeh
6. Hanlin Tang
7. Anastasia Koloskova
8. Hao Yu
9. Cong Xie
10. Filip Hanzely

Papers from Demjan Grubic's perspective

Ordered by how strongly the researchers Demjan Grubic 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. Long Short-Term Memory
4. Gradient-based learning applied to document recognition
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. ImageNet: A large-scale hierarchical image database
7. Attention is All you Need (Neural Information Processing Systems)
8. Learning Multiple Layers of Features from Tiny Images
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

• QSGD: Communication-Optimal Stochastic Gradient Descent, with Applications to Training Neural Networks (2016) — 391 citations
• Communication-Efficient Stochastic Gradient Descent, with Applications to Neural Networks (2017) — 7 citations
• QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding (2016) — 1,728 citations