Ohad Shamir
Artificial Intelligence · 2008–2020
A researcher in the Science corpus: 39 papers; trusts 955 researchers and is trusted by 2,652 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 492 citations into it; #488 of 36,961 by trust here, #701 by citations
- Optimization & Training — 252 citations into it; #69 of 2,605 by trust here, #105 by citations
- Computational Mechanics — 119 citations into it; #67 of 10,021 by trust here, #96 by citations
- Management Science and Operations Research — 111 citations into it; #104 of 12,201 by trust here, #111 by citations
- Computer Vision and Pattern Recognition — 101 citations into it; #4,270 of 21,973 by trust here, #4,388 by citations
- Statistical Learning Theory — 98 citations into it; #143 of 1,040 by trust here, #73 by citations
- Computational Theory and Mathematics — 73 citations into it; #1,804 of 12,489 by trust here, #1,497 by citations
- Scaling & Learning Theory — 68 citations into it; #98 of 429 by trust here, #177 by citations
Whom Ohad Shamir trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Shai Shalev-Shwartz
- Alekh Agarwal
- Yoshua Bengio
- John C. Duchi
- Elad Hazan
- Nati Srebro
- Geoffrey E. Hinton
- Tong Zhang
- Peter L. Bartlett
Who trusts Ohad Shamir overall
- Sebastian U. Stich
- Jakub Konecný
- Jason D. Lee
- Jialei Wang
- Nati Srebro
- Aymeric Dieuleveut
- Prateek Jain
- Zeyuan Allen-Zhu
- H. Brendan McMahan
- Yuchen Zhang
Papers from Ohad Shamir's perspective
Ordered by how strongly the researchers Ohad Shamir 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
- 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 Computational Efficiency of Training Neural Networks (2014) — 501 citations
- Size-Independent Sample Complexity of Neural Networks (2017) — 640 citations
- Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization (2011) — 839 citations
- Failures of Gradient-Based Deep Learning (2017) — 231 citations
- Optimal Distributed Online Prediction Using Mini-Batches (2010) — 724 citations
- The Power of Depth for Feedforward Neural Networks (2015) — 799 citations
- Better Mini-Batch Algorithms via Accelerated Gradient Methods (2011) — 330 citations
- On the Quality of the Initial Basin in Overspecified Neural Networks (2015) — 131 citations
- Trading Value and Information in MDPs (2012) — 104 citations
- Learnability, Stability and Uniform Convergence (2010) — 370 citations
- On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization (2012) — 210 citations
- Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes (2012) — 637 citations
- Communication-Efficient Distributed Optimization using an Approximate Newton-type Method (2013) — 601 citations
- Learning to classify with missing and corrupted features (2008) — 177 citations
- Spurious Local Minima are Common in Two-Layer ReLU Neural Networks (2017) — 286 citations
- Stochastic Convex Optimization (2009) — 349 citations
- Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimation (2013) — 113 citations
- Learning and generalization with the information bottleneck (2008) — 251 citations
- Communication Complexity of Distributed Convex Learning and Optimization (2015) — 225 citations
- Learning Kernel-Based Halfspaces with the 0-1 Loss (2011) — 62 citations