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
2023 | Conference Paper | IST-REx-ID: 14921 | 
Súkeník P, Mondelli M, Lampert C. Deep neural collapse is provably optimal for the deep unconstrained features model. In: 37th Annual Conference on Neural Information Processing Systems.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14924 |
Wu D, Kungurtsev V, Mondelli M. Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence. In: Transactions on Machine Learning Research. ML Research Press; 2023.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14923 |
Fu T, Liu Y, Barbier J, Mondelli M, Liang S, Hou T. Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise. In: Proceedings of 2023 IEEE International Symposium on Information Theory. IEEE. doi:10.1109/isit54713.2023.10206671
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14922 |
Esposito AR, Mondelli M. Concentration without independence via information measures. In: Proceedings of 2023 IEEE International Symposium on Information Theory. IEEE; 2023:400-405. doi:10.1109/isit54713.2023.10206899
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Journal Article | IST-REx-ID: 11420 |
Shevchenko A, Kungurtsev V, Mondelli M. Mean-field analysis of piecewise linear solutions for wide ReLU networks. Journal of Machine Learning Research. 2022;23(130):1-55.
[Published Version]
View
| Files available
| arXiv