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.




50 Publications

2023 | Published | Journal Article | IST-REx-ID: 12838 | OA
Zhang Y, Vatedka S. 2023. Multiple packing: Lower bounds via infinite constellations. IEEE Transactions on Information Theory. 69(7), 4513–4527.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 12859 | OA
Bombari S, Kiyani S, Mondelli M. 2023. Beyond the universal law of robustness: Sharper laws for random features and neural tangent kernels. Proceedings of the 40th International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 202, 2738–2776.
[Preprint] View | Files available | Download Preprint (ext.) | arXiv
 
2023 | Published | Journal Article | IST-REx-ID: 13269 | OA
Polyanskii N, Zhang Y. 2023. Codes for the Z-channel. IEEE Transactions on Information Theory. 69(10), 6340–6357.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
2023 | Published | Journal Article | IST-REx-ID: 13315 | OA
Barbier J, Camilli F, Mondelli M, Sáenz M. 2023. Fundamental limits in structured principal component analysis and how to reach them. Proceedings of the National Academy of Sciences of the United States of America. 120(30), e2302028120.
[Published Version] View | Files available | DOI | PubMed | Europe PMC
 
2023 | Published | Conference Paper | IST-REx-ID: 13321 | OA
Xu Y, Hou TQ, Liang SS, Mondelli M. 2023. Approximate message passing for multi-layer estimation in rotationally invariant models. 2023 IEEE Information Theory Workshop. ITW: Information Theory Workshop, 294–298.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 14083 | OA
Resch N, Yuan C, Zhang Y. 2023. Zero-rate thresholds and new capacity bounds for list-decoding and list-recovery. 50th International Colloquium on Automata, Languages, and Programming. ICALP: International Colloquium on Automata, Languages, and Programming, LIPIcs, vol. 261, 99.
[Published Version] View | Files available | DOI | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 14459 | OA
Shevchenko A, Kögler K, Hassani H, Mondelli M. 2023. Fundamental limits of two-layer autoencoders, and achieving them with gradient methods. Proceedings of the 40th International Conference on Machine Learning. ICML: International Conference on Machine Learning, PMLR, vol. 202, 31151–31209.
[Preprint] View | Download Preprint (ext.) | arXiv
 
2023 | Epub ahead of print | Journal Article | IST-REx-ID: 14665 | OA
Zhang Y, Vatedka S. 2023. Multiple packing: Lower bounds via error exponents. IEEE Transactions on Information Theory.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
2023 | Published | Journal Article | IST-REx-ID: 14751 | OA
Zhang Y. 2023. Zero-error communication over adversarial MACs. IEEE Transactions on Information Theory. 69(7), 4093–4127.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
2023 | In Press | Conference Paper | IST-REx-ID: 14921 | OA
Súkeník P, Mondelli M, Lampert C. Deep neural collapse is provably optimal for the deep unconstrained features model. 37th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, NeurIPS, .
[Preprint] View | Download Preprint (ext.) | arXiv
 
2023 | In Press | Conference Paper | IST-REx-ID: 14922 | OA
Esposito AR, Mondelli M. Concentration without independence via information measures. Proceedings of 2023 IEEE International Symposium on Information Theory. ISIT: IEEE International Symposium on Information Theory.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
2023 | In Press | Conference Paper | IST-REx-ID: 14923 | OA
Fu T, Liu Y, Barbier J, Mondelli M, Liang S, Hou T. Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise. Proceedings of 2023 IEEE International Symposium on Information Theory. ISIT: IEEE International Symposium on Information Theory.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 14924 | OA
Wu D, Kungurtsev V, Mondelli M. 2023. Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence. Transactions on Machine Learning Research. , TMLR, .
[Published Version] View | Download Published Version (ext.) | arXiv
 
2022 | Published | Journal Article | IST-REx-ID: 12273 | OA
Zhang Y, Vatedka S, Jaggi S, Sarwate AD. 2022. Quadratically constrained myopic adversarial channels. IEEE Transactions on Information Theory. 68(8), 4901–4948.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
2022 | Published | Journal Article | IST-REx-ID: 12480 | OA
Mondelli M, Venkataramanan R. 2022. Approximate message passing with spectral initialization for generalized linear models. Journal of Statistical Mechanics: Theory and Experiment. 2022(11), 114003.
[Published Version] View | Files available | DOI | WoS
 
2022 | Accepted | Preprint | IST-REx-ID: 12536 | OA
Barbier J, Hou T, Mondelli M, Saenz M. The price of ignorance: How much does it cost to forget noise structure in low-rank matrix estimation? arXiv, 2205.10009.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
2022 | Published | Conference Paper | IST-REx-ID: 12537 | OA
Bombari S, Amani MH, Mondelli M. 2022. Memorization and optimization in deep neural networks with minimum over-parameterization. 36th Conference on Neural Information Processing Systems. vol. 35, 7628–7640.
[Preprint] View | Download Preprint (ext.) | arXiv
 
2022 | Published | Journal Article | IST-REx-ID: 12538 | OA
Amani MH, Bombari S, Mondelli M, Pukdee R, Rini S. 2022. Sharp asymptotics on the compression of two-layer neural networks. IEEE Information Theory Workshop., 588–593.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
2022 | Published | Conference Paper | IST-REx-ID: 12540 | OA
Venkataramanan R, Kögler K, Mondelli M. 2022. Estimation in rotationally invariant generalized linear models via approximate message passing. Proceedings of the 39th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 162, 22.
[Published Version] View | Files available
 
2022 | Submitted | Preprint | IST-REx-ID: 12860 | OA
Bombari S, Achille A, Wang Z, Wang Y-X, Xie Y, Singh KY, Appalaraju S, Mahadevan V, Soatto S. Towards differential relational privacy and its use in question answering. arXiv, 2203.16701.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 

Filters and Search Terms

type<>research_data

Search

Filter Publications

Display / Sort

Citation Style: ISTA Annual Report

Export / Embed