Nati Srebro
Artificial Intelligence · 2003–2023
A researcher in the Science corpus: 68 papers; trusts 1,242 researchers and is trusted by 7,328 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 771 citations into it; #207 of 36,961 by trust here, #225 by citations
- Optimization & Training — 358 citations into it; #49 of 2,605 by trust here, #31 by citations
- Computational Mechanics — 259 citations into it; #33 of 10,021 by trust here, #33 by citations
- Computer Vision and Pattern Recognition — 186 citations into it; #845 of 21,973 by trust here, #992 by citations
- Statistical Learning Theory — 155 citations into it; #58 of 1,040 by trust here, #28 by citations
- Statistics and Probability — 144 citations into it; #1,146 of 13,188 by trust here, #962 by citations
- Computational Theory and Mathematics — 126 citations into it; #315 of 12,489 by trust here, #390 by citations
- Management Science and Operations Research — 118 citations into it; #127 of 12,201 by trust here, #102 by citations
Whom Nati Srebro trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Shai Shalev-Shwartz
- Tong Zhang
- Peter L. Bartlett
- Yurii E. Nesterov
- David A. McAllester
- Geoffrey E. Hinton
- Alex Krizhevsky
- L. Eon Bottou
- Ohad Shamir
- Yoshua Bengio
Who trusts Nati Srebro overall
- Behnam Neyshabur
- Ruslan Salakhutdinov
- Yongfeng Zhang
- Yoshua Bengio
- Francis R. Bach
- Jakub Konecný
- Jason D. Lee
- Ohad Shamir
- Martin Jaggi
- Tengyu Ma
Papers from Nati Srebro's perspective
Ordered by how strongly the researchers Nati Srebro 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
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Pegasos: primal estimated sub-gradient solver for SVM (2007) — 2,352 citations
- Equality of Opportunity in Supervised Learning (2016) — 5,258 citations
- The Marginal Value of Adaptive Gradient Methods in Machine Learning (2017) — 1,163 citations
- Exploring Generalization in Deep Learning (2017) — 1,437 citations
- A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks (2017) — 677 citations
- The Implicit Bias of Gradient Descent on Separable Data (2017) — 1,145 citations
- In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning (2014) — 729 citations
- Norm-Based Capacity Control in Neural Networks (2015) — 685 citations
- Uncovering shared structures in multiclass classification (2007) — 356 citations
- Path-SGD: Path-Normalized Optimization in Deep Neural Networks (2015) — 339 citations
- Maximum-Margin Matrix Factorization (2004) — 1,237 citations
- Fast maximum margin matrix factorization for collaborative prediction (2005) — 1,119 citations
- Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks (2018) — 403 citations
- Implicit Bias of Gradient Descent on Linear Convolutional Networks (2018) — 483 citations
- Better Mini-Batch Algorithms via Accelerated Gradient Methods (2011) — 330 citations
- Learning Non-Discriminatory Predictors (2017) — 404 citations
- SVM optimization: inverse dependence on training set size (2008) — 289 citations
- Weighted Low-Rank Approximations (2003) — 873 citations
- Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm (2013) — 621 citations
- Learnability, Stability and Uniform Convergence (2010) — 370 citations