Shuang Song
Artificial Intelligence · with Thakurta · 2013–2022
A researcher in the Science corpus: 14 papers; trusts 265 researchers and is trusted by 76 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 431 citations into it; #3,593 of 36,961 by trust here, #3,439 by citations
- Privacy & Security — 199 citations into it; #90 of 710 by trust here, #64 by citations
- Safety, Robustness & Interpretability — 84 citations into it; #1,597 of 2,259 by trust here, #1,373 by citations
- Computer Vision and Pattern Recognition — 53 citations into it
- Optimization & Training — 53 citations into it; #563 of 2,605 by trust here, #643 by citations
- Statistics and Probability — 50 citations into it; #7,357 of 13,188 by trust here, #6,272 by citations
- Sociology and Political Science — 44 citations into it
- Information Systems — 43 citations into it
Whom Shuang Song trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- Frank McSherry
- Kamalika Chaudhuri
- Alex Krizhevsky
- H. Brendan McMahan
- Adam D. Smith
- Ilya Mironov
- Kobbi Nissim
- John C. Duchi
- Yann LeCun
Who trusts Shuang Song overall
- Peter Kairouz
- Yu-Xiang Wang
- Abhradeep Thakurta
- Nicolas Papernot
- Milad Nasr
- Borja Balle
- Nicholas Carlini
- Florian Tramèr
- Raef Bassily
- Stephanie L. Hyland
Papers from Shuang Song's perspective
Ordered by how strongly the researchers Shuang Song 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
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Stochastic gradient descent with differentially private updates (2013) — 762 citations
- Scalable Private Learning with PATE (2018) — 725 citations
- Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning (2021) — 303 citations
- Membership Inference Attacks From First Principles (2021) — 1,168 citations
- Tempered Sigmoid Activations for Deep Learning with Differential Privacy (2020) — 220 citations
- Making the Shoe Fit: Architectures, Initializations, and Tuning for Learning with Privacy (2019) — 65 citations
- Measuring Forgetting of Memorized Training Examples (2022) — 150 citations
- Renyi Differential Privacy Mechanisms for Posterior Sampling (2017) — 64 citations
- Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems (2020) — 51 citations
- Pufferfish Privacy Mechanisms for Correlated Data (2016) — 172 citations
- Practical and Private (Deep) Learning without Sampling or Shuffling (2021) — 253 citations
- Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation (2020) — 94 citations
- Privacy-preserving Analysis of Correlated Data (2016) — 14 citations
- The Large Margin Mechanism for Differentially Private Maximization (2014) — 39 citations