Dan Alistarh
Artificial Intelligence · 2016–2023
A researcher in the Science corpus: 28 papers; trusts 1,927 researchers and is trusted by 158 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 628 citations into it; #3,103 of 36,961 by trust here, #2,542 by citations
- Computer Vision and Pattern Recognition — 384 citations into it; #4,006 of 21,973 by trust here, #2,531 by citations
- Optimization & Training — 249 citations into it; #327 of 2,605 by trust here, #263 by citations
- Efficiency & Compression — 241 citations into it; #56 of 1,273 by trust here, #88 by citations
- Computational Mechanics — 82 citations into it; #6,043 of 10,021 by trust here, #2,519 by citations
- Computer Networks and Communications — 82 citations into it; #3,849 of 9,996 by trust here, #3,729 by citations
- Model Architectures — 65 citations into it
- Large Language Models — 58 citations into it; #181 of 810 by trust here, #497 by citations
Whom Dan Alistarh trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Yann LeCun
- Diederik P. Kingma
- James Martens
- Yoshua Bengio
- Ilya Sutskever
- Karen Simonyan
- Jimmy Ba
Who trusts Dan Alistarh overall
- Sebastian U. Stich
- Cong Xie
- Elias Frantar
- Hanlin Tang
- Ahmed Khaled
- Sai Praneeth Karimireddy
- Peter Richtárik
- Anastasia Koloskova
- Martin Jaggi
- Lie He
Papers from Dan Alistarh's perspective
Ordered by how strongly the researchers Dan Alistarh 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)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- 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
- Model compression via distillation and quantization (2018) — 843 citations
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers (2022) — 2,286 citations
- QSGD: Communication-Optimal Stochastic Gradient Descent, with Applications to Training Neural Networks (2016) — 391 citations
- Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks (2021) — 986 citations
- SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot (2023) — 1,399 citations
- QSGD: Randomized Quantization for Communication-Optimal Stochastic Gradient Descent (2016) — 125 citations
- Byzantine Stochastic Gradient Descent (2018) — 324 citations
- ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning (2017) — 213 citations
- Distributed Learning over Unreliable Networks (2018) — 67 citations
- WoodFisher: Efficient second-order approximations for model compression (2020) — 31 citations
- The Convergence of Sparsified Gradient Methods (2018) — 553 citations
- SparCML: High-Performance Sparse Communication for Machine Learning (2018) — 149 citations
- SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression (2023) — 444 citations
- OPTQ: Accurate Quantization for Generative Pre-trained Transformers (2023) — 431 citations
- QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models (2023) — 55 citations
- Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning (2022) — 407 citations
- M-FAC: Efficient Matrix-Free Approximations of Second-Order Information (2021) — 66 citations
- How Well Do Sparse ImageNet Models Transfer? (2021) — 53 citations
- WoodFisher: Efficient Second-Order Approximation for Neural Network Compression (2020) — 209 citations
- Inducing and Exploiting Activation Sparsity for Fast Neural Network Inference (2020)