Sashank J. Reddi
Artificial Intelligence · 2014–2025
A researcher in the Science corpus: 28 papers; trusts 822 researchers and is trusted by 554 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 764 citations into it; #1,457 of 36,961 by trust here, #1,268 by citations
- Optimization & Training — 413 citations into it; #244 of 2,605 by trust here, #161 by citations
- Computational Mechanics — 197 citations into it; #1,076 of 10,021 by trust here, #542 by citations
- Computer Vision and Pattern Recognition — 136 citations into it
- Federated & Distributed Learning — 136 citations into it; #27 of 319 by trust here, #47 by citations
- Statistics and Probability — 102 citations into it; #6,206 of 13,188 by trust here, #1,257 by citations
- Computational Theory and Mathematics — 86 citations into it; #3,116 of 12,489 by trust here, #2,030 by citations
- Management Science and Operations Research — 74 citations into it
Whom Sashank J. Reddi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Tong Zhang
- Alex Krizhevsky
- Aaron Defazio
- Geoffrey E. Hinton
- Rie Johnson
- Diederik P. Kingma
- Francis R. Bach
- Shai Shalev-Shwartz
- Saeed Ghadimi
Who trusts Sashank J. Reddi overall
- Jakub Konecný
- Sai Praneeth Karimireddy
- Suvrit Sra
- Manzil Zaheer
- Zachary B. Charles
- Barnab'as P'oczos
- Chaoyue Liu
- Yang Song
- Samuel Horváth
- Peter Richtárik
Papers from Sashank J. Reddi's perspective
Ordered by how strongly the researchers Sashank J. Reddi 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 Convergence of Adam and Beyond (2018) — 2,997 citations
- Large Batch Optimization for Deep Learning: Training BERT in 76 minutes (2019) — 1,222 citations
- Stochastic Variance Reduction for Nonconvex Optimization (2016) — 654 citations
- Adaptive Methods for Nonconvex Optimization (2018) — 496 citations
- On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants (2015) — 200 citations
- On the Decreasing Power of Kernel and Distance Based Nonparametric Hypothesis Tests in High Dimensions (2014) — 215 citations
- SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning (2019) — 406 citations
- Adaptive Federated Optimization (2020) — 2,039 citations
- Are Transformers universal approximators of sequence-to-sequence functions? (2019) — 533 citations
- AIDE: Fast and Communication Efficient Distributed Optimization (2016) — 153 citations
- Fast Incremental Method for Nonconvex Optimization (2016) — 45 citations
- SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (2019) — 4,191 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
- A Field Guide to Federated Optimization (2021) — 487 citations
- Fast incremental method for smooth nonconvex optimization (2016) — 71 citations
- $O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers (2020) — 108 citations
- Stochastic Frank-Wolfe methods for nonconvex optimization (2016) — 158 citations
- On the High Dimensional Power of a Linear-Time Two Sample Test under Mean-shift Alternatives (2015) — 40 citations