Sanghamitra Dutta

Artificial Intelligence · 2017–2018

A researcher in the Science corpus: 4 papers; trusts 28 researchers and is trusted by 27 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 56 citations into it; #7,839 of 35,345 by trust here, #11,192 by citations
• Computer Networks and Communications — 56 citations into it; #2,331 of 9,886 by trust here, #3,318 by citations
• Optimization & Training — 34 citations into it; #2,332 of 2,601 by trust here, #1,942 by citations
• Computational Mechanics — 30 citations into it; #1,940 of 10,001 by trust here, #2,942 by citations
• ML Systems & Hardware — 20 citations into it; #85 of 575 by trust here, #270 by citations
• Information Systems — 17 citations into it
• Computer Vision and Pattern Recognition — 10 citations into it; #6,131 of 21,575 by trust here, #9,435 by citations
• Hardware and Architecture — 10 citations into it; #270 of 1,551 by trust here, #494 by citations

Whom Sanghamitra Dutta trusts overall

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

1. Yann LeCun
2. Gauri Joshi
3. Kangwook Lee
4. Rashish Tandon
5. Da Wang
6. Diederik P. Kingma
7. Muthu Dayalan
8. Geoffrey E. Hinton
9. Sebastian Ruder
10. E.J. Candes

Who trusts Sanghamitra Dutta overall

1. Deepesh Data
2. Zachary B. Charles
3. Qian Yu
4. Amirhossein Reisizadeh
5. Can Bülent Karakus
6. Suhas N. Diggavi
7. Jianyu Wang
8. Linqi Song
9. Amir Salman Avestimehr
10. Min Ye

Papers from Sanghamitra Dutta's perspective

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

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
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. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD (2018) — 217 citations
• A Unified Coded Deep Neural Network Training Strategy based on Generalized PolyDot codes (2018) — 116 citations
• “Short-Dot”: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products (2017) — 395 citations
• Coded convolution for parallel and distributed computing within a deadline (2017) — 147 citations