Amar Phanishayee

Artificial Intelligence · 2008–2021

A researcher in the Science corpus: 16 papers; trusts 402 researchers and is trusted by 15 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 197 citations into it; #11,331 of 35,345 by trust here, #3,797 by citations
• Computer Vision and Pattern Recognition — 163 citations into it; #11,871 of 21,575 by trust here, #3,929 by citations
• Optimization & Training — 107 citations into it; #1,658 of 2,601 by trust here, #548 by citations
• Computer Networks and Communications — 78 citations into it; #8,622 of 9,886 by trust here, #1,297 by citations
• Hardware and Architecture — 56 citations into it
• Model Architectures — 56 citations into it
• ML Systems & Hardware — 55 citations into it
• Efficiency & Compression — 49 citations into it; #594 of 1,264 by trust here, #297 by citations

Whom Amar Phanishayee trusts overall

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

1. Alex Krizhevsky
2. Kaiming He
3. Geoffrey E. Hinton
4. Karen Simonyan
5. Yoshua Bengio
6. Ilya Sutskever
7. Yann LeCun
8. Diederik P. Kingma
9. Sergey Ioffe
10. Christian Szegedy

Who trusts Amar Phanishayee overall

1. D. Narayanan
2. Samyam Rajbhandari
3. Haitao Wu
4. Chaoyang He
5. Mohammad Alizadeh
6. Keshav Santhanam
7. Wencong Xiao
8. Zachary B. Charles
9. Vijay Anand Korthikanti
10. Hong-You Chen

Papers from Amar Phanishayee's perspective

Ordered by how strongly the researchers Amar Phanishayee 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. Going deeper with convolutions
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM (2021) — 1,287 citations
• PipeDream: generalized pipeline parallelism for DNN training (2019) — 1,228 citations
• Memory-Efficient Pipeline-Parallel DNN Training (2020) — 299 citations
• PipeDream: Fast and Efficient Pipeline Parallel DNN Training (2018) — 317 citations
• Gist: Efficient Data Encoding for Deep Neural Network Training (2018) — 155 citations
• Efficient Algorithms for Device Placement of DNN Graph Operators (2020) — 81 citations
• Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads (2019) — 471 citations
• Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads (2020) — 300 citations
• The Non-IID Data Quagmire of Decentralized Machine Learning (2019) — 692 citations
• Efficient Large-Scale Language Model Training on GPU Clusters (2021) — 108 citations
• Themis: Fair and Efficient GPU Cluster Scheduling for Machine Learning Workloads (2019) — 249 citations
• PipeDream: Pipeline Parallelism for DNN Training (2018)
• Multi-tenant GPU Clusters for Deep Learning Workloads: Analysis and Implications (2018) — 71 citations
• ProjecToR: Agile Reconfigurable Data Center Interconnect (2016) — 348 citations
• Safe and effective fine-grained TCP retransmissions for datacenter communication (2009) — 499 citations
• Measurement and Analysis of TCP Throughput Collapse in Cluster-based Storage Systems (2008) — 295 citations