J. Demmel
Artificial Intelligence · 1997–2019
A researcher in the Science corpus: 30 papers; trusts 416 researchers and is trusted by 86 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 136 citations into it; #12,604 of 36,961 by trust here, #4,263 by citations
- Optimization & Training — 106 citations into it; #565 of 2,605 by trust here, #347 by citations
- Hardware and Architecture — 80 citations into it; #68 of 1,731 by trust here, #211 by citations
- Computer Vision and Pattern Recognition — 79 citations into it; #14,362 of 21,973 by trust here, #3,657 by citations
- Computational Theory and Mathematics — 62 citations into it; #760 of 12,489 by trust here, #440 by citations
- Computer Networks and Communications — 56 citations into it; #2,075 of 9,996 by trust here, #1,642 by citations
- Computational Mechanics — 25 citations into it
- ML Systems & Hardware — 21 citations into it
Whom J. Demmel trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Jean B. Lasserre
- Didier Henrion
- Iain S. Duff
- Pablo A. Parrilo
- Kaiming He
- Dror Irony
- Mark Hoemmen
- R. Vuduc
- Geoffrey E. Hinton
Who trusts J. Demmel overall
- Grey Ballard
- Yuji Nakatsukasa
- Noam Shazeer
- Xiaoye Sherry Li
- Per-Gunnar Martinsson
- Stefano Grivet-Talocia
- Edgar Solomonik
- Ana Marco
- Santo Fortunato
- R. Vuduc
Papers from J. Demmel's perspective
Ordered by how strongly the researchers J. Demmel 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)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Large Batch Optimization for Deep Learning: Training BERT in 76 minutes (2019) — 1,222 citations
- ImageNet Training in Minutes (2017) — 470 citations
- Communication-Optimal Parallel 2.5D Matrix Multiplication and LU Factorization Algorithms (2011) — 262 citations
- Communication optimal parallel multiplication of sparse random matrices (2013) — 118 citations
- Communication-Optimal Convolutional Neural Nets (2018) — 22 citations
- Reducing BERT Pre-Training Time from 3 Days to 76 Minutes (2019) — 126 citations
- 100-epoch ImageNet Training with AlexNet in 24 Minutes (2017) — 61 citations
- Templates for the Solution of Algebraic Eigenvalue Problems (2000) — 1,679 citations
- Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects (2009) — 486 citations
- Communication-optimal Parallel and Sequential QR and LU Factorizations (2008) — 483 citations
- Minimizing Communication in Numerical Linear Algebra (2009) — 281 citations
- The Probability That a Numerical, Analysis Problem Is Difficult (2013) — 163 citations
- Fast linear algebra is stable (2006) — 265 citations
- Benchmarking GPUs to tune dense linear algebra (2008) — 970 citations
- On condition numbers and the distance to the nearest ill-posed problem (2015) — 313 citations
- IEEE Standard for Floating-Point Arithmetic (2008) — 2,319 citations
- Communication-Optimal Parallel Recursive Rectangular Matrix Multiplication (2013) — 126 citations
- SuperLU Users'' Guide (1997)
- Precimonious: Tuning assistant for floating-point precision (2013) — 331 citations
- Communication lower bounds and optimal algorithms for programs that reference arrays - Part 1 (2013) — 82 citations