Please note that LibreCat no longer supports Internet Explorer versions 8 or 9 (or earlier).
We recommend upgrading to the latest Internet Explorer, Google Chrome, or Firefox.
148 Publications
2024 | Published | Conference Paper | IST-REx-ID: 17093 | 
Communication-efficient federated learning with data and client heterogeneity
H. Zakerinia, S. Talaei, G. Nadiradze, D.-A. Alistarh, in:, Proceedings of the 27th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2024, pp. 3448–3456.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
H. Zakerinia, S. Talaei, G. Nadiradze, D.-A. Alistarh, in:, Proceedings of the 27th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2024, pp. 3448–3456.
2024 | Published | Conference Paper | IST-REx-ID: 17332 |
Wait-free trees with asymptotically-efficient range queries
I. Kokorin, V. Yudov, V. Aksenov, D.-A. Alistarh, in:, 2024 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2024, pp. 169–179.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
I. Kokorin, V. Yudov, V. Aksenov, D.-A. Alistarh, in:, 2024 IEEE International Parallel and Distributed Processing Symposium, IEEE, 2024, pp. 169–179.
2024 | Published | Conference Paper | IST-REx-ID: 15011 |
How to prune your language model: Recovering accuracy on the "Sparsity May Cry" benchmark
E. Kurtic, T. Hoefler, D.-A. Alistarh, in:, Proceedings of Machine Learning Research, ML Research Press, 2024, pp. 542–553.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
E. Kurtic, T. Hoefler, D.-A. Alistarh, in:, Proceedings of Machine Learning Research, ML Research Press, 2024, pp. 542–553.
2024 | Published | Conference Paper | IST-REx-ID: 18070
Federated SGD with local asynchrony
B. Chatterjee, V. Kungurtsev, D.-A. Alistarh, in:, Proceedings of the 44th International Conference on Distributed Computing Systems, IEEE, 2024, pp. 857–868.
View
| DOI
B. Chatterjee, V. Kungurtsev, D.-A. Alistarh, in:, Proceedings of the 44th International Conference on Distributed Computing Systems, IEEE, 2024, pp. 857–868.
2024 | Published | Conference Paper | IST-REx-ID: 18113 |
Extreme compression of large language models via additive quantization
V. Egiazarian, A. Panferov, D. Kuznedelev, E. Frantar, A. Babenko, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 12284–12303.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
V. Egiazarian, A. Panferov, D. Kuznedelev, E. Frantar, A. Babenko, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 12284–12303.
2024 | Published | Conference Paper | IST-REx-ID: 18117 |
RoSA: Accurate parameter-efficient fine-tuning via robust adaptation
M. Nikdan, S. Tabesh, E. Crncevic, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 38187–38206.
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
M. Nikdan, S. Tabesh, E. Crncevic, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 38187–38206.
2024 | Published | Conference Paper | IST-REx-ID: 18975 |
Error feedback can accurately compress preconditioners
I.-V. Modoranu, A. Kalinov, E. Kurtic, E. Frantar, D.-A. Alistarh, in:, 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 35910–35933.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
I.-V. Modoranu, A. Kalinov, E. Kurtic, E. Frantar, D.-A. Alistarh, in:, 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 35910–35933.
2024 | Published | Conference Paper | IST-REx-ID: 18977 |
SpQR: A sparse-quantized representation for near-lossless LLM weight compression
T. Dettmers, R.A. Svirschevski, V. Egiazarian, D. Kuznedelev, E. Frantar, S. Ashkboos, A. Borzunov, T. Hoefler, D.-A. Alistarh, in:, 12th International Conference on Learning Representations, OpenReview, 2024.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
T. Dettmers, R.A. Svirschevski, V. Egiazarian, D. Kuznedelev, E. Frantar, S. Ashkboos, A. Borzunov, T. Hoefler, D.-A. Alistarh, in:, 12th International Conference on Learning Representations, OpenReview, 2024.
2024 | Published | Conference Paper | IST-REx-ID: 19519 |
PV-tuning: Beyond straight-through estimation for extreme LLM compression
Malinovskii, Vladimir, PV-tuning: Beyond straight-through estimation for extreme LLM compression. 38th Conference on Neural Information Processing Systems 37. 2024
[Published Version]
View
| Files available
| arXiv
Malinovskii, Vladimir, PV-tuning: Beyond straight-through estimation for extreme LLM compression. 38th Conference on Neural Information Processing Systems 37. 2024
2024 | Published | Conference Paper | IST-REx-ID: 19511 |
QuaRot: Outlier-free 4-bit inference in rotated LLMs
Ashkboos, Saleh, QuaRot: Outlier-free 4-bit inference in rotated LLMs. 38th Conference on Neural Information Processing Systems 37. 2024
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
Ashkboos, Saleh, QuaRot: Outlier-free 4-bit inference in rotated LLMs. 38th Conference on Neural Information Processing Systems 37. 2024
2024 | Published | Conference Paper | IST-REx-ID: 18121 |
SPADE: Sparsity-guided debugging for deep neural networks
A.S. Moakhar, E.B. Iofinova, E. Frantar, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 45955–45987.
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
A.S. Moakhar, E.B. Iofinova, E. Frantar, D.-A. Alistarh, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 45955–45987.
2024 | Published | Thesis | IST-REx-ID: 17485 |
Compressing large neural networks : Algorithms, systems and scaling laws
E. Frantar, Compressing Large Neural Networks : Algorithms, Systems and Scaling Laws, Institute of Science and Technology Austria, 2024.
[Published Version]
View
| Files available
| DOI
E. Frantar, Compressing Large Neural Networks : Algorithms, Systems and Scaling Laws, Institute of Science and Technology Austria, 2024.
2024 | Published | Conference Paper | IST-REx-ID: 18061 |
QMoE: Sub-1-bit compression of trillion parameter models
E. Frantar, D.-A. Alistarh, in:, P. Gibbons, G. Pekhimenko, C. De Sa (Eds.), Proceedings of Machine Learning and Systems, 2024.
[Published Version]
View
| Files available
| Download Published Version (ext.)
E. Frantar, D.-A. Alistarh, in:, P. Gibbons, G. Pekhimenko, C. De Sa (Eds.), Proceedings of Machine Learning and Systems, 2024.
2024 | Published | Conference Paper | IST-REx-ID: 18062 |
Scaling laws for sparsely-connected foundation models
E. Frantar, C.R. Ruiz, N. Houlsby, D.-A. Alistarh, U. Evci, in:, The Twelfth International Conference on Learning Representations, 2024.
[Published Version]
View
| Files available
| Download Published Version (ext.)
| arXiv
E. Frantar, C.R. Ruiz, N. Houlsby, D.-A. Alistarh, U. Evci, in:, The Twelfth International Conference on Learning Representations, 2024.
2024 | Published | Thesis | IST-REx-ID: 17490 |
Communication-efficient distributed training of deep neural networks: An algorithms and systems perspective
I. Markov, Communication-Efficient Distributed Training of Deep Neural Networks: An Algorithms and Systems Perspective, Institute of Science and Technology Austria, 2024.
[Published Version]
View
| Files available
| DOI
I. Markov, Communication-Efficient Distributed Training of Deep Neural Networks: An Algorithms and Systems Perspective, Institute of Science and Technology Austria, 2024.
2024 | Published | Conference Paper | IST-REx-ID: 17456 |
L-GreCo: Layerwise-adaptive gradient compression for efficient data-parallel deep learning
I. Markov, K. Alimohammadi, E. Frantar, D.-A. Alistarh, in:, P. Gibbons, G. Pekhimenko, C. De Sa (Eds.), Proceedings of Machine Learning and Systems , Association for Computing Machinery, 2024.
[Published Version]
View
| Files available
| Download Published Version (ext.)
| arXiv
I. Markov, K. Alimohammadi, E. Frantar, D.-A. Alistarh, in:, P. Gibbons, G. Pekhimenko, C. De Sa (Eds.), Proceedings of Machine Learning and Systems , Association for Computing Machinery, 2024.
2024 | Published | Conference Paper | IST-REx-ID: 17329 |
Game dynamics and equilibrium computation in the population protocol model
D.-A. Alistarh, K. Chatterjee, M. Karrabi, J.M. Lazarsfeld, in:, Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing, Association for Computing Machinery, 2024, pp. 40–49.
[Published Version]
View
| Files available
| DOI
D.-A. Alistarh, K. Chatterjee, M. Karrabi, J.M. Lazarsfeld, in:, Proceedings of the 43rd Annual ACM Symposium on Principles of Distributed Computing, Association for Computing Machinery, 2024, pp. 40–49.
2024 | Published | Conference Paper | IST-REx-ID: 18976 |
AsGrad: A sharp unified analysis of asynchronous-SGD algorithms
R. Islamov, M. Safaryan, D.-A. Alistarh, in:, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2024, pp. 649–657.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
R. Islamov, M. Safaryan, D.-A. Alistarh, in:, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2024, pp. 649–657.
2024 | Published | Conference Paper | IST-REx-ID: 19518 |
The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information
Wu, Diyuan, The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information. 38th Conference on Neural Information Processing Systems 37. 2024
[Preprint]
View
| Download Preprint (ext.)
| arXiv
Wu, Diyuan, The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information. 38th Conference on Neural Information Processing Systems 37. 2024
2024 | Published | Conference Paper | IST-REx-ID: 19510 |
MICROADAM: Accurate adaptive optimization with low space overhead and provable convergence
Modoranu, Ionut-Vlad, MICROADAM: Accurate adaptive optimization with low space overhead and provable convergence. 38th Conference on Neural Information Processing Systems 37. 2024
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
Modoranu, Ionut-Vlad, MICROADAM: Accurate adaptive optimization with low space overhead and provable convergence. 38th Conference on Neural Information Processing Systems 37. 2024