Urmăriți
Dan Alistarh
Dan Alistarh
Professor at IST Austria
Adresă de e-mail confirmată pe ist.ac.at - Pagina de pornire
Titlu
Citat de
Citat de
Anul
QSGD: Communication-efficient SGD via gradient quantization and encoding
D Alistarh, D Grubic, J Li, R Tomioka, M Vojnovic
Advances in neural information processing systems 30, 2017
21352017
Gptq: Accurate post-training quantization for generative pre-trained transformers
E Frantar, S Ashkboos, T Hoefler, D Alistarh
arXiv preprint arXiv:2210.17323, 2022
11222022
Model compression via distillation and quantization
A Polino, R Pascanu, D Alistarh
ICLR 2018, 2018
9352018
Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks
T Hoefler, D Alistarh, T Ben-Nun, N Dryden, A Peste
Journal of Machine Learning Research 22 (241), 1-124, 2021
9242021
Sparsegpt: Massive language models can be accurately pruned in one-shot
E Frantar, D Alistarh
International Conference on Machine Learning, 10323-10337, 2023
6372023
The convergence of sparsified gradient methods
D Alistarh, T Hoefler, M Johansson, N Konstantinov, S Khirirat, C Renggli
Advances in Neural Information Processing Systems 31, 2018
6232018
Byzantine stochastic gradient descent
D Alistarh, Z Allen-Zhu, J Li
Advances in neural information processing systems 31, 2018
3602018
ZipML: Training linear models with end-to-end low precision, and a little bit of deep learning
H Zhang, J Li, K Kara, D Alistarh, J Liu, C Zhang
International Conference on Machine Learning, 4035-4043, 2017
256*2017
Optimal brain compression: A framework for accurate post-training quantization and pruning
E Frantar, D Alistarh
Advances in Neural Information Processing Systems 35, 4475-4488, 2022
2452022
Spqr: A sparse-quantized representation for near-lossless llm weight compression
T Dettmers, R Svirschevski, V Egiazarian, D Kuznedelev, E Frantar, ...
arXiv preprint arXiv:2306.03078, 2023
2302023
Inducing and exploiting activation sparsity for fast inference on deep neural networks
M Kurtz, J Kopinsky, R Gelashvili, A Matveev, J Carr, M Goin, W Leiserson, ...
International Conference on Machine Learning, 5533-5543, 2020
1832020
Woodfisher: Efficient second-order approximation for neural network compression
SP Singh, D Alistarh
Advances in Neural Information Processing Systems 33, 18098-18109, 2020
1792020
SparCML: High-performance sparse communication for machine learning
C Renggli, S Ashkboos, M Aghagolzadeh, D Alistarh, T Hoefler
Proceedings of the International Conference for High Performance Computing …, 2019
1542019
Time-space trade-offs in population protocols
D Alistarh, J Aspnes, D Eisenstat, R Gelashvili, RL Rivest
Proceedings of the twenty-eighth annual ACM-SIAM symposium on discrete …, 2017
1532017
The spraylist: A scalable relaxed priority queue
D Alistarh, J Kopinsky, J Li, N Shavit
Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of …, 2015
1512015
The optimal bert surgeon: Scalable and accurate second-order pruning for large language models
E Kurtic, D Campos, T Nguyen, E Frantar, M Kurtz, B Fineran, M Goin, ...
arXiv preprint arXiv:2203.07259, 2022
1392022
Fast and exact majority in population protocols
D Alistarh, R Gelashvili, M Vojnović
Proceedings of the 2015 ACM Symposium on Principles of Distributed Computing …, 2015
1312015
Space-optimal majority in population protocols
D Alistarh, J Aspnes, R Gelashvili
Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete …, 2018
1292018
Quarot: Outlier-free 4-bit inference in rotated llms
S Ashkboos, A Mohtashami, M Croci, B Li, P Cameron, M Jaggi, D Alistarh, ...
Advances in Neural Information Processing Systems 37, 100213-100240, 2024
1132024
Polylogarithmic-time leader election in population protocols
D Alistarh, R Gelashvili
International Colloquium on Automata, Languages, and Programming, 479-491, 2015
1132015
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20