Dan Alistarh

QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding

Dan Alistarh, Demjan Grubic, Jerry Li et al. · arXiv (Cornell University) · 2016 · 906 citations · Full text

Engineering, Machine Learning, Data Science +15

Model compression via distillation and quantization

Antonio Polino, Razvan Pascanu, Dan Alistarh · arXiv (Cornell University) · 2018 · 262 citations · Full text

Artificial Intelligence, Convolutional Neural Network, Engineering +16

GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Elias Frantar, Saleh Ashkboos, Torsten Hoefler et al. · arXiv (Cornell University) · 2022 · 126 citations · Full text

Propose Gptq, Engineering, Machine Learning +17

Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks

Torsten Hoefler, Dan Alistarh, Tal Ben‐Nun et al. · Repository for Publications and Research Data (ETH Zurich) · 2021 · 125 citations · Full text

Artificial Intelligence, Pruned Parameter Efficiency, Sparse Representation +14

ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning

Hantian Zhang, Jerry Li, Kaan Kara et al. · International Conference on Machine Learning · 2017 · 118 citations

Large Ai Model, Engineering, Machine Learning +7