Suvrit Sra
Artificial Intelligence · 2004–2023
A researcher in the Science corpus: 32 papers; trusts 1,150 researchers and is trusted by 154 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 486 citations into it; #2,808 of 36,961 by trust here, #2,563 by citations
- Optimization & Training — 301 citations into it; #828 of 2,605 by trust here, #513 by citations
- Computational Mechanics — 239 citations into it; #688 of 10,021 by trust here, #379 by citations
- Computer Vision and Pattern Recognition — 141 citations into it; #7,555 of 21,973 by trust here, #6,563 by citations
- Computational Theory and Mathematics — 131 citations into it; #4,750 of 12,489 by trust here, #3,623 by citations
- Numerical Analysis — 114 citations into it; #778 of 3,703 by trust here, #648 by citations
- Statistics and Probability — 103 citations into it; #7,288 of 13,188 by trust here, #1,876 by citations
- Management Science and Operations Research — 77 citations into it; #9,618 of 12,201 by trust here, #10,633 by citations
Whom Suvrit Sra trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Dimitri P. Bertsekas
- Geoffrey E. Hinton
- Alex Krizhevsky
- Francis R. Bach
- John C. Duchi
- Diederik P. Kingma
- Radford M. Neal
- Tong Zhang
- Yoshua Bengio
Who trusts Suvrit Sra overall
- Sashank J. Reddi
- Zhiwu Huang
- Nicolas Loizou
- Mehrtash Harandi
- Brandon Amos
- Luc Van Gool
- Lam M. Nguyen
- Francis R. Bach
- Manzil Zaheer
- Barnab'as P'oczos
Papers from Suvrit Sra's perspective
Ordered by how strongly the researchers Suvrit Sra 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
- Information-theoretic metric learning (2006) — 2,131 citations
- Contrastive Learning with Hard Negative Samples (2020) — 1,052 citations
- Stochastic Variance Reduction for Nonconvex Optimization (2016) — 654 citations
- On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants (2015) — 200 citations
- Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity (2019) — 627 citations
- Fast Incremental Method for Nonconvex Optimization (2016) — 45 citations
- Fast Stochastic Methods for Nonsmooth Nonconvex Optimization (2016) — 54 citations
- Why ADAM Beats SGD for Attention Models (2019) — 88 citations
- A Generic Approach for Escaping Saddle points (2017) — 87 citations
- Reflection methods for user-friendly submodular optimization (2013) — 80 citations
- Global optimality conditions for deep neural networks (2017) — 128 citations
- Fast incremental method for smooth nonconvex optimization (2016) — 71 citations
- AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization (2015) — 31 citations
- Diversity Networks (2015) — 128 citations
- Stochastic Frank-Wolfe methods for nonconvex optimization (2016) — 158 citations
- Minimum Sum-Squared Residue Co-Clustering of Gene Expression Data (2004) — 329 citations
- Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms (2014) — 44 citations
- SGD with shuffling: optimal rates without component convexity and large epoch requirements (2020) — 77 citations
- Escaping Saddle Points with Adaptive Gradient Methods (2019) — 84 citations
- Transformers learn to implement preconditioned gradient descent for in-context learning (2023) — 311 citations