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.
52 Publications
2022 | Journal Article | IST-REx-ID: 10364 | 
Hashemi, S. A., Mondelli, M., Fazeli, A., Vardy, A., Cioffi, J., & Goldsmith, A. (2022). Parallelism versus latency in simplified successive-cancellation decoding of polar codes. IEEE Transactions on Wireless Communications. Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/TWC.2021.3125626
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2022 | Journal Article | IST-REx-ID: 12538 |
Amani, M. H., Bombari, S., Mondelli, M., Pukdee, R., & Rini, S. (2022). Sharp asymptotics on the compression of two-layer neural networks. IEEE Information Theory Workshop. Mumbai, India: IEEE. https://doi.org/10.1109/ITW54588.2022.9965870
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Conference Paper | IST-REx-ID: 12537 |
Bombari, S., Amani, M. H., & Mondelli, M. (2022). Memorization and optimization in deep neural networks with minimum over-parameterization. In 36th Conference on Neural Information Processing Systems (Vol. 35, pp. 7628–7640). Curran Associates.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Journal Article | IST-REx-ID: 12480 |
Mondelli, M., & Venkataramanan, R. (2022). Approximate message passing with spectral initialization for generalized linear models. Journal of Statistical Mechanics: Theory and Experiment. IOP Publishing. https://doi.org/10.1088/1742-5468/ac9828
[Published Version]
View
| Files available
| DOI
| WoS
2021 | Conference Paper | IST-REx-ID: 10595 |
Nguyen, Q., Mondelli, M., & Montufar, G. F. (2021). Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep ReLU networks. In M. Meila & T. Zhang (Eds.), Proceedings of the 38th International Conference on Machine Learning (Vol. 139, pp. 8119–8129). Virtual: ML Research Press.
[Published Version]
View
| Download Published Version (ext.)
| arXiv