Thomas Steinke
Artificial Intelligence · 2011–2021
A researcher in the Science corpus: 19 papers; trusts 174 researchers and is trusted by 119 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 411 citations into it; #2,488 of 36,961 by trust here, #2,549 by citations
- Privacy & Security — 242 citations into it; #54 of 710 by trust here, #78 by citations
- Statistics and Probability — 84 citations into it
- Computational Theory and Mathematics — 79 citations into it; #2,154 of 12,489 by trust here, #3,208 by citations
- Safety, Robustness & Interpretability — 43 citations into it
- Computer Networks and Communications — 39 citations into it; #7,096 of 9,996 by trust here, #1,998 by citations
- Electrical and Electronic Engineering — 35 citations into it
- Statistical Learning Theory — 33 citations into it; #270 of 1,040 by trust here, #180 by citations
Whom Thomas Steinke trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- Mark Bun
- Jonathan Ullman
- Frank McSherry
- Moritz Hardt
- Kobbi Nissim
- Adam D. Smith
- Kunal Talwar
- Aaron Roth
- Gábor Tardos
Who trusts Thomas Steinke overall
- Mark Bun
- Jonathan Ullman
- Vitaly Feldman
- Yu-Xiang Wang
- Gautam Kamath
- Cynthia Dwork
- Ryan M. Rogers
- Salil P. Vadhan
- Ilya Mironov
- Adam D. Smith
Papers from Thomas Steinke's perspective
Ordered by how strongly the researchers Thomas Steinke 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
- Learning Multiple Layers of Features from Tiny Images
- Calibrating Noise to Sensitivity in Private Data Analysis
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Revealing information while preserving privacy
Their papers
- A Hybrid Approach to Privacy-Preserving Federated Learning (2018) — 1,112 citations
- Algorithmic stability for adaptive data analysis (2015) — 304 citations
- The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation (2021) — 307 citations
- Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation (2019) — 88 citations
- Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds (2016) — 1,008 citations
- Robust Traceability from Trace Amounts (2015) — 192 citations
- Interactive fingerprinting codes and the hardness of preventing false discovery (2014) — 119 citations
- Generalization for Adaptively-chosen Estimators via Stable Median (2017) — 48 citations
- Tight Lower Bounds for Differentially Private Selection (2017) — 85 citations
- Composable and versatile privacy via truncated CDP (2018) — 191 citations
- Differential Privacy: A Primer for a Non-Technical Audience (2018) — 228 citations
- Private Hypothesis Selection (2019) — 101 citations
- The Discrete Gaussian for Differential Privacy (2020) — 345 citations
- Exposed! A Survey of Attacks on Private Data (2017) — 314 citations
- Calibrating Noise to Variance in Adaptive Data Analysis (2017) — 57 citations
- Make Up Your Mind: The Price of Online Queries in Differential Privacy (2016) — 66 citations
- More General Queries and Less Generalization Error in Adaptive Data Analysis (2015) — 15 citations
- Between Pure and Approximate Differential Privacy (2015) — 176 citations
- Molecular simulation grid (2011) — 5 citations