Abhradeep Thakurta
Artificial Intelligence · 2009–2023
A researcher in the Science corpus: 35 papers; trusts 492 researchers and is trusted by 209 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 838 citations into it; #1,962 of 36,961 by trust here, #1,603 by citations
- Privacy & Security — 411 citations into it; #23 of 710 by trust here, #18 by citations
- Statistics and Probability — 157 citations into it; #2,985 of 13,188 by trust here, #2,468 by citations
- Safety, Robustness & Interpretability — 149 citations into it; #842 of 2,259 by trust here, #744 by citations
- Optimization & Training — 137 citations into it; #377 of 2,605 by trust here, #501 by citations
- Computational Theory and Mathematics — 110 citations into it
- Management Science and Operations Research — 101 citations into it; #3,170 of 12,201 by trust here, #1,828 by citations
- Sociology and Political Science — 93 citations into it
Whom Abhradeep Thakurta trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- Adam D. Smith
- Kamalika Chaudhuri
- Frank McSherry
- Kobbi Nissim
- Shai Shalev-Shwartz
- Shiva Prasad Kasiviswanathan
- Moritz Hardt
- Kunal Talwar
- Robert Tibshirani
Who trusts Abhradeep Thakurta overall
- Raef Bassily
- Yu-Xiang Wang
- Kunal Talwar
- Vitaly Feldman
- Adam D. Smith
- Mark Bun
- Peter Kairouz
- Prateek Jain
- Jonathan Ullman
- Shuang Song
Papers from Abhradeep Thakurta's perspective
Ordered by how strongly the researchers Abhradeep Thakurta trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Learning Multiple Layers of Features from Tiny Images
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- 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
- Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning (2021) — 303 citations
- Privacy Amplification by Iteration (2018) — 205 citations
- Private Convex Optimization for Empirical Risk Minimization with Applications to High-dimensional Regression (2012) — 298 citations
- Towards Practical Differentially Private Convex Optimization (2019) — 203 citations
- Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds (2014) — 830 citations
- Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds (2014) — 364 citations
- Tempered Sigmoid Activations for Deep Learning with Differential Privacy (2020) — 220 citations
- Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity (2018) — 512 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
- Differentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso (2013) — 180 citations
- Discovering frequent patterns in sensitive data (2010) — 284 citations
- Private Stochastic Convex Optimization with Optimal Rates (2019) — 273 citations
- To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout (2015) — 33 citations
- Privacy Amplification via Random Check-Ins (2020) — 81 citations
- Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems (2020) — 51 citations
- How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy (2023) — 300 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
- Dimension Independence in Unconstrained Private ERM via Adaptive Preconditioning (2020) — 14 citations