Peter Kairouz
Artificial Intelligence · 2013–2021
A researcher in the Science corpus: 26 papers; trusts 583 researchers and is trusted by 123 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,306 citations into it; #2,910 of 36,961 by trust here, #1,760 by citations
- Privacy & Security — 508 citations into it; #51 of 710 by trust here, #58 by citations
- Optimization & Training — 247 citations into it
- Safety, Robustness & Interpretability — 234 citations into it
- Federated & Distributed Learning — 233 citations into it; #124 of 319 by trust here, #25 by citations
- Computer Networks and Communications — 191 citations into it
- Computer Vision and Pattern Recognition — 172 citations into it
- Statistics and Probability — 141 citations into it; #1,406 of 13,188 by trust here, #1,143 by citations
Whom Peter Kairouz trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- H. Brendan McMahan
- Ilya Mironov
- Frank McSherry
- John C. Duchi
- Kobbi Nissim
- Kamalika Chaudhuri
- Moritz Hardt
- Alex Krizhevsky
- Geoffrey E. Hinton
Who trusts Peter Kairouz overall
- Borja Balle
- Min Ye
- Jayadev Acharya
- Wei-Ning Chen
- Sewoong Oh
- Pramod Viswanath
- Zinan Lin
- Aurélien Bellet
- Wenlong Mou
- Quan Geng
Papers from Peter Kairouz's perspective
Ordered by how strongly the researchers Peter Kairouz 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
- Learning Multiple Layers of Features from Tiny Images
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Advances and Open Problems in Federated Learning (2019) — 9,019 citations
- The Composition Theorem for Differential Privacy (2013) — 825 citations
- Can You Really Backdoor Federated Learning? (2019) — 742 citations
- Generative Models for Effective ML on Private, Decentralized Datasets (2019) — 211 citations
- A Field Guide to Federated Optimization (2021) — 487 citations
- The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation (2021) — 307 citations
- Theoretical Guarantees for Model Auditing with Finite Adversaries (2019)
- DP-CGAN: Differentially Private Synthetic Data and Label Generation (2019) — 282 citations
- Extremal Mechanisms for Local Differential Privacy (2014) — 667 citations
- Discrete Distribution Estimation under Local Privacy (2016) — 377 citations
- Federated Heavy Hitters Discovery with Differential Privacy (2019) — 116 citations
- Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs (2020) — 26 citations
- Privacy Amplification via Random Check-Ins (2020) — 81 citations
- The Staircase Mechanism in Differential Privacy (2015) — 174 citations
- Breaking the Communication-Privacy-Accuracy Trilemma (2020) — 139 citations
- Breaking The Dimension Dependence in Sparse Distribution Estimation under Communication Constraints (2021) — 11 citations
- Practical and Private (Deep) Learning without Sampling or Shuffling (2021) — 253 citations
- Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning (2021) — 321 citations
- Dimension Independence in Unconstrained Private ERM via Adaptive Preconditioning (2020) — 14 citations
- Learning Generative Adversarial RePresentations (GAP) under Fairness and Censoring Constraints (2019) — 22 citations