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.
118 Publications
2020 | Conference Paper | IST-REx-ID: 9632 | 
Singh SP, Alistarh D-A. 2020. WoodFisher: Efficient second-order approximation for neural network compression. Advances in Neural Information Processing Systems. NeurIPS: Conference on Neural Information Processing Systems vol. 33, 18098–18109.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2020 | Conference Paper | IST-REx-ID: 9631 |
Aksenov V, Alistarh D-A, Korhonen J. 2020. Scalable belief propagation via relaxed scheduling. Advances in Neural Information Processing Systems. NeurIPS: Conference on Neural Information Processing Systems vol. 33, 22361–22372.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2020 | Conference Paper | IST-REx-ID: 9415 |
Kurtz M, Kopinsky J, Gelashvili R, Matveev A, Carr J, Goin M, Leiserson W, Moore S, Nell B, Shavit N, Alistarh D-A. 2020. Inducing and exploiting activation sparsity for fast neural network inference. 37th International Conference on Machine Learning, ICML 2020. ICML: International Conference on Machine Learning vol. 119, 5533–5543.
[Published Version]
View
| Files available
2020 | Journal Article | IST-REx-ID: 8268 |
Gurel NM, Kara K, Stojanov A, Smith T, Lemmin T, Alistarh D-A, Puschel M, Zhang C. 2020. Compressive sensing using iterative hard thresholding with low precision data representation: Theory and applications. IEEE Transactions on Signal Processing. 68, 4268–4282.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2020 | Conference Paper | IST-REx-ID: 8722 |
Li S, Tal Ben-Nun TB-N, Girolamo SD, Alistarh D-A, Hoefler T. 2020. Taming unbalanced training workloads in deep learning with partial collective operations. Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. PPoPP: Sympopsium on Principles and Practice of Parallel Programming, 45–61.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv