Om Thakkar
Artificial Intelligence · 2016–2022
A researcher in the Science corpus: 11 papers; trusts 133 researchers and is trusted by 17 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 315 citations into it; #9,105 of 35,345 by trust here, #6,720 by citations
- Privacy & Security — 177 citations into it; #394 of 709 by trust here, #276 by citations
- Safety, Robustness & Interpretability — 74 citations into it; #1,295 of 2,251 by trust here, #1,650 by citations
- Optimization & Training — 69 citations into it; #1,958 of 2,601 by trust here, #1,585 by citations
- Statistics and Probability — 45 citations into it
- Computer Vision and Pattern Recognition — 32 citations into it
- Computer Science Applications — 28 citations into it
- Federated & Distributed Learning — 27 citations into it
Whom Om Thakkar trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- H. Brendan McMahan
- Cynthia Dwork
- Shai Shalev-Shwartz
- Kamalika Chaudhuri
- Kunal Talwar
- Diederik P. Kingma
- Frank McSherry
- Martín Abadi
- Geoffrey E. Hinton
- Adam D. Smith
Who trusts Om Thakkar overall
- Peter Kairouz
- Nicholas Carlini
- Florian Tramèr
- Daphne Ippolito
- Natalia Ponomareva
- Chiyuan Zhang
- Zachary B. Charles
- Matthew Jagielski
- Shuang Song
- Abhradeep Thakurta
Papers from Om Thakkar's perspective
Ordered by how strongly the researchers Om Thakkar 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
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Going deeper with convolutions
Their papers
- Training Production Language Models without Memorizing User Data (2020) — 97 citations
- Understanding Unintended Memorization in Federated Learning (2020) — 49 citations
- Towards Practical Differentially Private Convex Optimization (2019) — 203 citations
- Measuring Forgetting of Memorized Training Examples (2022) — 150 citations
- Differentially Private Learning with Adaptive Clipping (2019) — 454 citations
- Max-Information, Differential Privacy, and Post-selection Hypothesis Testing (2016) — 91 citations
- Privacy Amplification via Random Check-Ins (2020) — 81 citations
- Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems (2020) — 51 citations
- Practical and Private (Deep) Learning without Sampling or Shuffling (2021) — 253 citations
- Differentially Private Learning with Adaptive Clipping (2019) — 9 citations
- Differentially Private Matrix Completion, Revisited (2017) — 34 citations