Aaron Defazio
Artificial Intelligence · 2014–2021
A researcher in the Science corpus: 10 papers; trusts 286 researchers and is trusted by 677 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 117 citations into it; #1,205 of 36,961 by trust here, #3,544 by citations
- Optimization & Training — 87 citations into it; #111 of 2,605 by trust here, #309 by citations
- Computational Mechanics — 52 citations into it; #110 of 10,021 by trust here, #283 by citations
- Computer Vision and Pattern Recognition — 41 citations into it; #5,036 of 21,973 by trust here, #10,782 by citations
- Management Science and Operations Research — 19 citations into it
- Control and Systems Engineering — 17 citations into it; #2,948 of 8,519 by trust here, #6,664 by citations
- Reinforcement Learning — 15 citations into it; #1,146 of 2,250 by trust here, #2,097 by citations
- Evaluation & Benchmarks — 12 citations into it; #1,367 of 3,155 by trust here, #2,979 by citations
Whom Aaron Defazio trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Shai Shalev-Shwartz
- Tong Zhang
- Julien Mairal
- Rie Johnson
- Francis R. Bach
- Mark W. Schmidt
- Yurii E. Nesterov
- Chih-Jen Lin
- Yann LeCun
- Geoffrey E. Hinton
Who trusts Aaron Defazio overall
- Peter Richtárik
- Nicolas Loizou
- Jakub Konecný
- Zeyuan Allen-Zhu
- Sashank J. Reddi
- Filip Hanzely
- Konstantin Mishchenko
- Aryan Mokhtari
- Samuel Horváth
- Francis R. Bach
Papers from Aaron Defazio's perspective
Ordered by how strongly the researchers Aaron Defazio 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
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives (2014) — 2,012 citations
- Finito: A faster, permutable incremental gradient method for big data problems (2014) — 172 citations
- A Simple Practical Accelerated Method for Finite Sums (2016) — 124 citations
- On the Ineffectiveness of Variance Reduced Optimization for Deep Learning (2018) — 127 citations
- Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields (2015) — 83 citations
- A Comparison of learning algorithms on the Arcade Learning Environment (2014) — 26 citations
- fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning. (2020) — 514 citations
- Stochastic Polyak Stepsize with a Moving Target (2021) — 21 citations
- End-to-End Variational Networks for Accelerated MRI Reconstruction (2020) — 436 citations
- fastMRI: An Open Dataset and Benchmarks for Accelerated MRI (2018) — 1,072 citations