Sai Praneeth Karimireddy

Artificial Intelligence · 2018–2021

A researcher in the Science corpus: 14 papers; trusts 422 researchers and is trusted by 45 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 553 citations into it; #8,538 of 35,345 by trust here, #5,720 by citations
• Optimization & Training — 328 citations into it; #539 of 2,601 by trust here, #692 by citations
• Federated & Distributed Learning — 172 citations into it; #116 of 319 by trust here, #69 by citations
• Computational Mechanics — 151 citations into it; #8,079 of 10,001 by trust here, #8,566 by citations
• Computer Vision and Pattern Recognition — 87 citations into it; #8,429 of 21,575 by trust here, #6,371 by citations
• Computer Networks and Communications — 71 citations into it
• Statistics and Probability — 59 citations into it
• Efficiency & Compression — 57 citations into it; #187 of 1,264 by trust here, #559 by citations

Whom Sai Praneeth Karimireddy trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Yurii E. Nesterov
2. Francis R. Bach
3. Sebastian U. Stich
4. Alex Krizhevsky
5. Kaiming He
6. Geoffrey E. Hinton
7. L. Eon Bottou
8. Diederik P. Kingma
9. Yoshua Bengio
10. Yann LeCun

Who trusts Sai Praneeth Karimireddy overall

1. Sebastian U. Stich
2. Martin Jaggi
3. Ahmed Khaled
4. Jianyu Wang
5. Tao Lin
6. Yae Jee Cho
7. Cong Xie
8. Sashank J. Reddi
9. Farzin Haddadpour
10. Qinbin Li

Papers from Sai Praneeth Karimireddy's perspective

Ordered by how strongly the researchers Sai Praneeth Karimireddy trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Attention is All you Need (Neural Information Processing Systems)
8. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization (2019) — 446 citations
• Why ADAM Beats SGD for Attention Models (2019) — 88 citations
• Error Feedback Fixes SignSGD and other Gradient Compression Schemes (2019) — 655 citations
• SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning (2019) — 406 citations
• Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients (2018) — 63 citations
• A Field Guide to Federated Optimization (2021) — 487 citations
• Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning (2020) — 251 citations
• Why are Adaptive Methods Good for Attention Models? (2020) — 381 citations
• Byzantine-Robust Learning on Heterogeneous Datasets via Resampling (2020) — 42 citations
• Secure Byzantine-Robust Machine Learning (2020) — 68 citations
• Learning from History for Byzantine Robust Optimization (2020) — 260 citations
• The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication (2019) — 184 citations
• SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (2019) — 4,191 citations
• Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems (2018) — 18 citations