Li Zhang
Artificial Intelligence · with Talwar · 2012–2019
A researcher in the Science corpus: 10 papers; trusts 138 researchers and is trusted by 128 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 230 citations into it; #2,789 of 36,961 by trust here, #1,652 by citations
- Privacy & Security — 116 citations into it; #73 of 710 by trust here, #59 by citations
- Statistics and Probability — 39 citations into it; #11,222 of 13,188 by trust here, #8,124 by citations
- Optimization & Training — 38 citations into it
- Computational Theory and Mathematics — 35 citations into it; #2,626 of 12,489 by trust here, #2,583 by citations
- Safety, Robustness & Interpretability — 31 citations into it; #292 of 2,259 by trust here, #120 by citations
- Management Science and Operations Research — 24 citations into it
- Sociology and Political Science — 24 citations into it; #22,056 of 22,891 by trust here, #17,066 by citations
Whom Li Zhang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- Frank McSherry
- Moritz Hardt
- Kunal Talwar
- Kobbi Nissim
- Adam D. Smith
- Abhradeep Thakurta
- Aaron Roth
- Alex Krizhevsky
- Mark Bun
Who trusts Li Zhang overall
- Peter Kairouz
- Salil P. Vadhan
- Florian Tramèr
- H. Brendan McMahan
- Lingjuan Lyu
- Jonathan Ullman
- Om Thakkar
- Congzheng Song
- Abhradeep Thakurta
- Thomas Steinke
Papers from Li Zhang's perspective
Ordered by how strongly the researchers Li Zhang trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Gradient-based learning applied to document recognition
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Learning Multiple Layers of Features from Tiny Images
- Long Short-Term Memory
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- ImageNet: A large-scale hierarchical image database
- Going deeper with convolutions
- Attention is All you Need (Neural Information Processing Systems)
Their papers
- Deep Learning with Differential Privacy (2016) — 8,077 citations
- Rényi Differential Privacy of the Sampled Gaussian Mechanism (2019) — 347 citations
- On the Protection of Private Information in Machine Learning Systems: Two Recent Approches (2017) — 50 citations
- Learning Differentially Private Language Models Without Losing Accuracy (2017) — 129 citations
- The geometry of differential privacy: the sparse and approximate cases (2012) — 233 citations
- Private False Discovery Rate Control (2015) — 28 citations
- The Geometry of Differential Privacy: The Small Database and Approximate Cases (2016) — 32 citations
- Learning Differentially Private Recurrent Language Models (2017) — 1,510 citations
- Nearly Optimal Private LASSO (2015) — 163 citations
- Analyze gauss: optimal bounds for privacy-preserving principal component analysis (2014) — 338 citations