Satyen Kale
Artificial Intelligence · 2006–2021
A researcher in the Science corpus: 20 papers; trusts 404 researchers and is trusted by 1,395 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 506 citations into it; #817 of 36,961 by trust here, #1,259 by citations
- Optimization & Training — 227 citations into it; #195 of 2,605 by trust here, #302 by citations
- Federated & Distributed Learning — 128 citations into it; #115 of 319 by trust here, #69 by citations
- Computational Mechanics — 93 citations into it; #1,660 of 10,021 by trust here, #2,519 by citations
- Management Science and Operations Research — 84 citations into it; #132 of 12,201 by trust here, #115 by citations
- Computer Vision and Pattern Recognition — 73 citations into it
- Computer Networks and Communications — 62 citations into it; #2,638 of 9,996 by trust here, #7,240 by citations
- Statistics and Probability — 47 citations into it; #4,600 of 13,188 by trust here, #1,143 by citations
Whom Satyen Kale trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Martin A. Zinkevich
- Yurii E. Nesterov
- Elad Hazan
- Alex Krizhevsky
- L. Eon Bottou
- Geoffrey E. Hinton
- Diederik P. Kingma
- Nicolò Cesa-Bianchi
- Peter Auer
- Tong Zhang
Who trusts Satyen Kale overall
- Zeyuan Allen-Zhu
- Elad Hazan
- Alekh Agarwal
- Ohad Shamir
- Francis R. Bach
- Aleksandrs Slivkins
- Lijun Zhang
- John C. Duchi
- Vitaly Feldman
- Julien Mairal
Papers from Satyen Kale's perspective
Ordered by how strongly the researchers Satyen Kale 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
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- On the Convergence of Adam and Beyond (2018) — 2,997 citations
- Logarithmic regret algorithms for online convex optimization (2006) — 1,314 citations
- Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits (2014) — 564 citations
- Adaptive Methods for Nonconvex Optimization (2018) — 496 citations
- The Multiplicative Weights Update Method: a Meta-Algorithm and Applications (2012) — 1,187 citations
- SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning (2019) — 406 citations
- Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization (2011) — 252 citations
- Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization (2014) — 237 citations
- Efficient Optimal Learning for Contextual Bandits (2011) — 325 citations
- SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (2019) — 4,191 citations
- A combinatorial, primal-dual approach to semidefinite programs (2007) — 295 citations
- An optimal algorithm for stochastic strongly-convex optimization (2010) — 19 citations
- Privacy, accuracy, and consistency too: a holistic solution to contingency table release (2007) — 556 citations
- A Field Guide to Federated Optimization (2021) — 487 citations
- The uniform hardcore lemma via approximate Bregman projections (2009) — 68 citations
- Better Algorithms for Benign Bandits (2009) — 94 citations
- Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning (2020) — 251 citations
- Estimating Training Data Influence by Tracking Gradient Descent (2020) — 704 citations
- Escaping Saddle Points with Adaptive Gradient Methods (2019) — 84 citations
- Non-Stochastic Bandit Slate Problems (2010) — 95 citations