Michael W. Mahoney
Artificial Intelligence · Neural Information Processing Systems · 2000–2023
A researcher in the Science corpus: 53 papers; trusts 2,607 researchers and is trusted by 282 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,147 citations into it; #2,057 of 36,961 by trust here, #1,677 by citations
- Computer Vision and Pattern Recognition — 715 citations into it; #3,985 of 21,973 by trust here, #1,764 by citations
- Efficiency & Compression — 358 citations into it; #241 of 1,273 by trust here, #198 by citations
- Optimization & Training — 313 citations into it; #380 of 2,605 by trust here, #626 by citations
- Statistical and Nonlinear Physics — 286 citations into it; #1,426 of 10,175 by trust here, #520 by citations
- Model Architectures — 202 citations into it
- Computational Theory and Mathematics — 179 citations into it; #365 of 12,489 by trust here, #885 by citations
- Computational Mechanics — 163 citations into it; #127 of 10,021 by trust here, #239 by citations
Whom Michael W. Mahoney trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Petros Drineas
- Yoshua Bengio
- Alex Krizhevsky
- Geoffrey E. Hinton
- Francis R. Bach
- Kaiming He
- Yann LeCun
- Diederik P. Kingma
- Ilya Sutskever
- L. Eon Bottou
Who trusts Michael W. Mahoney overall
- David P. Woodruff
- Petros Drineas
- A. Alaoui
- Shusen Wang
- Francis R. Bach
- Farbod Roosta-Khorasani
- Peter Bhlmann
- Per-Gunnar Martinsson
- Alex Gittens
- Alessandro Rudi
Papers from Michael W. Mahoney's perspective
Ordered by how strongly the researchers Michael W. Mahoney 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT (2019) — 675 citations
- Hessian-based Analysis of Large Batch Training and Robustness to Adversaries (2018) — 194 citations
- ZeroQ: A Novel Zero Shot Quantization Framework (2020) — 496 citations
- PyHessian: Neural Networks Through the Lens of the Hessian (2019) — 401 citations
- On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent (2018) — 82 citations
- HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision (2019) — 686 citations
- A Survey of Quantization Methods for Efficient Neural Network Inference (2021) — 1,633 citations
- Fast Randomized Kernel Methods With Statistical Guarantees (2014) — 93 citations
- Random Laplace Feature Maps for Semigroup Kernels on Histograms (2014) — 54 citations
- I-BERT: Integer-only BERT Quantization (2021) — 459 citations
- Revisiting the Nystrom Method for Improved Large-scale Machine Learning (2013) — 461 citations
- A Berkeley View of Systems Challenges for AI (2017) — 213 citations
- Continuous-in-Depth Neural Networks (2020) — 56 citations
- HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks (2019) — 394 citations
- Sub-Sampled Newton Methods II: Local Convergence Rates (2016) — 86 citations
- GIANT: Globally Improved Approximate Newton Method for Distributed Optimization (2017) — 148 citations
- Fast Randomized Kernel Ridge Regression with Statistical Guarantees (2015) — 326 citations
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning (2020) — 383 citations
- Skip-Gram − Zipf + Uniform = Vector Additivity (2017) — 98 citations
- Fast approximation of matrix coherence and statistical leverage (2011) — 583 citations