H. Brendan McMahan
Artificial Intelligence · 2003–2023
A researcher in the Science corpus: 46 papers; trusts 1,015 researchers and is trusted by 1,506 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,512 citations into it; #753 of 36,961 by trust here, #178 by citations
- Optimization & Training — 494 citations into it; #104 of 2,605 by trust here, #70 by citations
- Privacy & Security — 468 citations into it; #42 of 710 by trust here, #10 by citations
- Computer Vision and Pattern Recognition — 230 citations into it; #6,483 of 21,973 by trust here, #9,347 by citations
- Computer Networks and Communications — 224 citations into it; #173 of 9,996 by trust here, #335 by citations
- Federated & Distributed Learning — 223 citations into it; #1 of 319 by trust here, #1 by citations
- Safety, Robustness & Interpretability — 200 citations into it; #262 of 2,259 by trust here, #105 by citations
- Computational Mechanics — 170 citations into it; #562 of 10,021 by trust here, #810 by citations
Whom H. Brendan McMahan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Shai Shalev-Shwartz
- John C. Duchi
- Yurii E. Nesterov
- Alex Krizhevsky
- Cynthia Dwork
- Geoffrey E. Hinton
- Martin A. Zinkevich
- Lin Xiao
- Yoshua Bengio
- Yann LeCun
Who trusts H. Brendan McMahan overall
- Peter Kairouz
- Jakub Konecný
- Om Thakkar
- Cong Xie
- Lingjuan Lyu
- Tian Li
- Yang Liu
- Lichao Sun
- Zachary B. Charles
- Chaoyang He
Papers from H. Brendan McMahan's perspective
Ordered by how strongly the researchers H. Brendan McMahan 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
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Deep Learning with Differential Privacy (2016) — 8,077 citations
- Communication-Efficient Learning of Deep Networks from Decentralized Data (2016) — 25,704 citations
- Federated Learning: Strategies for Improving Communication Efficiency (2016) — 5,508 citations
- Online convex optimization in the bandit setting: gradient descent without a gradient (2004) — 1,009 citations
- Practical Secure Aggregation for Privacy-Preserving Machine Learning (2017) — 4,229 citations
- Ad click prediction: a view from the trenches (2013) — 1,043 citations
- Towards Federated Learning at Scale: System Design (2019) — 3,255 citations
- LEAF: A Benchmark for Federated Settings (2018) — 1,782 citations
- Advances and Open Problems in Federated Learning (2019) — 9,019 citations
- Estimation, Optimization, and Parallelism when Data is Sparse (2013) — 105 citations
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence (2016) — 2,231 citations
- Federated Optimization: Distributed Optimization Beyond the Datacenter (2015) — 823 citations
- Distributed Mean Estimation with Limited Communication (2016) — 400 citations
- cpSGD: Communication-efficient and differentially-private distributed SGD (2018) — 548 citations
- A General Approach to Adding Differential Privacy to Iterative Training Procedures (2018) — 216 citations
- Federated Learning of Deep Networks using Model Averaging (2016) — 1,281 citations
- Planning in the Presence of Cost Functions Controlled by an Adversary (2003) — 384 citations
- Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization (2018) — 128 citations
- Training Production Language Models without Memorizing User Data (2020) — 97 citations
- Adaptive Federated Optimization (2020) — 2,039 citations