Badih Ghazi

Artificial Intelligence · 2016–2025

A researcher in the Science corpus: 14 papers; trusts 116 researchers and is trusted by 30 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 688 citations into it; #4,889 of 35,345 by trust here, #2,368 by citations
• Privacy & Security — 418 citations into it; #116 of 709 by trust here, #164 by citations
• Federated & Distributed Learning — 140 citations into it; #201 of 319 by trust here, #44 by citations
• Optimization & Training — 116 citations into it
• Safety, Robustness & Interpretability — 108 citations into it
• Computational Theory and Mathematics — 98 citations into it; #3,516 of 12,182 by trust here, #3,117 by citations
• Computer Networks and Communications — 71 citations into it
• Statistics and Probability — 69 citations into it

Whom Badih Ghazi trusts overall

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

1. Cynthia Dwork
2. Ú. Erlingsson
3. Kobbi Nissim
4. Borja Balle
5. Adam D. Smith
6. Ilya Mironov
7. Albert Cheu
8. Frank McSherry
9. Yuval Ishai
10. Rasmus Pagh

Who trusts Badih Ghazi overall

1. Albert Cheu
2. Ravi Kumar
3. Pasin Manurangsi
4. Victor Balcer
5. Alisa Chang
6. Borja Balle
7. Rasmus Pagh
8. Peter Kairouz
9. James Bell
10. Amos Beimel

Papers from Badih Ghazi's perspective

Ordered by how strongly the researchers Badih Ghazi 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. Attention is All you Need (Neural Information Processing Systems)
6. Long Short-Term Memory
7. Learning Multiple Layers of Features from Tiny Images
8. ImageNet: A large-scale hierarchical image database
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)

Their papers

• Advances and Open Problems in Federated Learning (2019) — 9,019 citations
• Large-Scale Differentially Private BERT (2021) — 162 citations
• Private Aggregation from Fewer Anonymous Messages (2019) — 57 citations
• Scalable and Differentially Private Distributed Aggregation in the Shuffled Model (2019) — 105 citations
• The Optimality of Correlated Sampling (2016) — 13 citations
• Decidability of Non-interactive Simulation of Joint Distributions (2016) — 35 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• Locally Private k-Means in One Round (2021) — 42 citations
• Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message (2021) — 45 citations
• On Distributed Differential Privacy and Counting Distinct Elements (2020) — 35 citations
• Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead (2020) — 60 citations
• Pure Differentially Private Summation from Anonymous Messages (2020) — 51 citations
• Private Heavy Hitters and Range Queries in the Shuffled Model (2019) — 6 citations
• On the Power of Multiple Anonymous Messages (2019) — 112 citations