Phillip B. Gibbons
Artificial Intelligence · 2000–2019
A researcher in the Science corpus: 42 papers; trusts 892 researchers and is trusted by 86 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 691 citations into it; #6,541 of 36,961 by trust here, #1,844 by citations
- Computer Networks and Communications — 250 citations into it; #636 of 9,996 by trust here, #179 by citations
- Computer Vision and Pattern Recognition — 230 citations into it; #16,869 of 21,973 by trust here, #4,945 by citations
- Privacy & Security — 198 citations into it
- Optimization & Training — 189 citations into it; #1,394 of 2,605 by trust here, #495 by citations
- Information Systems — 137 citations into it; #583 of 9,233 by trust here, #278 by citations
- Hardware and Architecture — 117 citations into it; #909 of 1,731 by trust here, #246 by citations
- Safety, Robustness & Interpretability — 77 citations into it
Whom Phillip B. Gibbons trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yoshua Bengio
- Samuel Madden
- Yann LeCun
- Kaiming He
- Christian Szegedy
- Ilya Sutskever
- Diederik P. Kingma
- Karen Simonyan
Who trusts Phillip B. Gibbons overall
- Ross Goldingay
- Binghui Wang
- David B. Lindenmayer
- Neil Zhenqiang Gong
- K. Cockle
- J. Fischer
- C. McElhinny
- A. Manning
- Will Steffen
- Daniel Simberloff
Papers from Phillip B. Gibbons's perspective
Ordered by how strongly the researchers Phillip B. Gibbons trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- 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
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Going deeper with convolutions
- Learning Multiple Layers of Features from Tiny Images
Their papers
- PipeDream: generalized pipeline parallelism for DNN training (2019) — 1,228 citations
- Advances and Open Problems in Federated Learning (2019) — 9,019 citations
- PipeDream: Fast and Efficient Pipeline Parallel DNN Training (2018) — 317 citations
- More Effective Distributed ML via a Stale Synchronous Parallel Parameter Server (2013) — 813 citations
- GeePS: scalable deep learning on distributed GPUs with a GPU-specialized parameter server (2016) — 337 citations
- The Non-IID Data Quagmire of Decentralized Machine Learning (2019) — 692 citations
- Avoiding bio‐perversity from carbon sequestration solutions (2012) — 132 citations
- SysML: The New Frontier of Machine Learning Systems (2019) — 23 citations
- MLSys: The New Frontier of Machine Learning Systems (2019) — 25 citations
- PipeDream: Pipeline Parallelism for DNN Training (2018)
- Focus: Querying Large Video Datasets with Low Latency and Low Cost (2018) — 304 citations
- Ambit: In-Memory Accelerator for Bulk Bitwise Operations Using Commodity DRAM Technology (2017) — 638 citations
- Gaia: Geo-Distributed Machine Learning Approaching LAN Speeds (2017) — 450 citations
- Taming a Wicked Problem: Resolving Controversies in Biodiversity Offsetting (2016) — 256 citations
- Zorua: A holistic approach to resource virtualization in GPUs (2016) — 67 citations
- Addressing the straggler problem for iterative convergent parallel ML (2016) — 148 citations
- Scalable deep learning on distributed GPUs with a GPU-specialized parameter server (2015)
- Exploiting iterative-ness for parallel ML computations (2014) — 40 citations
- Exploiting Bounded Staleness to Speed Up Big Data Analytics (2014) — 171 citations
- RowClone: Fast and energy-efficient in-DRAM bulk data copy and initialization (2013) — 491 citations