S. Sundararajan
Optimization & Training · 2008–2014
A researcher in the Science corpus: 6 papers; trusts 56 researchers and is trusted by 41 researchers here, as inferred from the citation graph.
Subfields
- Optimization & Training — 42 citations into it; #2,447 of 2,601 by trust here, #2,519 by citations
- Artificial Intelligence — 39 citations into it; #5,003 of 35,345 by trust here, #7,531 by citations
- Computational Mechanics — 15 citations into it; #3,988 of 10,001 by trust here, #5,350 by citations
- Computer Vision and Pattern Recognition — 14 citations into it; #5,115 of 21,575 by trust here, #5,941 by citations
- Natural Language Processing — 8 citations into it
- Control and Systems Engineering — 6 citations into it
- Statistical Learning Theory — 6 citations into it; #391 of 1,038 by trust here, #309 by citations
- Mathematical Optimization — 6 citations into it
Whom S. Sundararajan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Thorsten Joachims
- L. Eon Bottou
- Peter Richtárik
- Yurii E. Nesterov
- Chih-Jen Lin
- Shai Shalev-Shwartz
- Gideon S. Mann
- Thomas Finley
- Michael Patriksson
- Dong C. Liu
Who trusts S. Sundararajan overall
- Dhruv Kumar Mahajan
- Peter Richtárik
- Martin Takác
- Shusen Wang
- Shun Zheng
- Vojtech Franc
- Virginia Smith
- Martin Jaggi
- Tong Zhang
- Jakub Konecný
Papers from S. Sundararajan's perspective
Ordered by how strongly the researchers S. Sundararajan trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- 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
- A dual coordinate descent method for large-scale linear SVM (2008) — 1,036 citations
- A Functional Approximation Based Distributed Learning Algorithm (2013) — 18 citations
- A Parallel SGD method with Strong Convergence (2013) — 16 citations
- A Sequential Dual Method for Structural SVMs (2011) — 27 citations
- A distributed block coordinate descent method for training $l_1$ regularized linear classifiers (2014) — 36 citations
- Tractable Semi-supervised Learning of Complex Structured Prediction Models (2013) — 11 citations