Please note that ISTA Research Explorer no longer supports Internet Explorer versions 8 or 9 (or earlier).

We recommend upgrading to the latest Internet Explorer, Google Chrome, or Firefox.

82 Publications


2025 | Published | Conference Paper | IST-REx-ID: 20033 | OA
Emrullah Ildiz M, Gozeten HA, Taga EO, Mondelli M, Oymak S. High-dimensional analysis of knowledge distillation: Weak-to-Strong generalization and scaling laws. In: 13th International Conference on Learning Representations. ICLR; 2025:2967-3006.
[Published Version] View | Files available | arXiv
 

2025 | Published | Conference Paper | IST-REx-ID: 20035 | OA
Jacot A, Súkeník P, Wang Z, Mondelli M. Wide neural networks trained with weight decay provably exhibit neural collapse. In: 13th International Conference on Learning Representations. ICLR; 2025:1905-1931.
[Published Version] View | Files available | arXiv
 

2025 | Epub ahead of print | Journal Article | IST-REx-ID: 20081 | OA
Esposito AR, Gastpar M, Issa I. Sibson α-mutual information and its variational representations. IEEE Transactions on Information Theory. 2025. doi:10.1109/TIT.2025.3587340
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 

2025 | Published | Conference Paper | IST-REx-ID: 20300 | OA
Wegel T, Kovačević F, Ţifrea A, Yang F. Learning Pareto manifolds in high dimensions: How can regularization help? In: The 28th International Conference on Artificial Intelligence and Statistics. Vol 258. ML Research Press; 2025:4591-4599.
[Preprint] View | Download Preprint (ext.) | arXiv
 

2025 | Published | Conference Paper | IST-REx-ID: 20667
El Latif Kadry A, Zhang Y, Weinberger N. Mean estimation in high-dimensional binary timeinhomogeneous Markov Gaussian mixture models. In: 2025 IEEE International Symposium on Information Theory Proceedings. IEEE; 2025. doi:10.1109/ISIT63088.2025.11195426
View | DOI
 

2025 | Published | Journal Article | IST-REx-ID: 20734 | OA | PlanS
Zhang Y, Ji HC, Venkataramanan R, Mondelli M. Spectral estimators for structured generalized linear models via approximate message passing. Mathematical Statistics and Learning. 2025;8(3-4):193-304. doi:10.4171/MSL/52
[Published Version] View | Files available | DOI
 

2025 | Published | Journal Article | IST-REx-ID: 18986 | OA
Barbier J, Camilli F, Xu Y, Mondelli M. Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise. Physical Review Research. 2025;7. doi:10.1103/PhysRevResearch.7.013081
[Published Version] View | Files available | DOI | arXiv
 

2025 | Published | Journal Article | IST-REx-ID: 19065 | OA | PlanS
Fornasier M, Klock T, Mondelli M, Rauchensteiner M. Efficient identification of wide shallow neural networks with biases. Applied and Computational Harmonic Analysis. 2025;77. doi:10.1016/j.acha.2025.101749
[Published Version] View | Files available | DOI | WoS
 

2025 | Published | Conference Paper | IST-REx-ID: 19281 | OA
Resch N, Yuan C, Zhang Y. Tight bounds on list-decodable and list-recoverable zero-rate codes. In: 16th Innovations in Theoretical Computer Science Conference. Vol 325. Schloss Dagstuhl - Leibniz-Zentrum für Informatik; 2025. doi:10.4230/LIPIcs.ITCS.2025.82
[Published Version] View | Files available | DOI | WoS | arXiv
 

2025 | Published | Journal Article | IST-REx-ID: 19627 | OA
Bombari S, Mondelli M. Privacy for free in the overparameterized regime. Proceedings of the National Academy of Sciences. 2025;122(15). doi:10.1073/pnas.2423072122
[Published Version] View | Files available | DOI | WoS | PubMed | Europe PMC | arXiv
 

2025 | Published | Conference Paper | IST-REx-ID: 21324 | OA
Bombari S, Mondelli M. Spurious correlations in high dimensional regression: The roles of regularization, simplicity bias and over-parameterization. In: Proceedings of the 42nd International Conference on Machine Learning. Vol 267. ML Research Press; 2025:4839-4873.
[Published Version] View | Files available | arXiv
 

2025 | Published | Conference Paper | IST-REx-ID: 21325 | OA
Gozeten HA, Ildiz ME, Zhang X, Soltanolkotabi M, Mondelli M, Oymak S. Test-time training provably improves transformers as in-context learners. In: Proceedings of the 42nd International Conference on Machine Learning. Vol 267. ML Research Press; 2025:20266-20295.
[Published Version] View | Files available | PubMed | Europe PMC
 

2025 | Published | Conference Paper | IST-REx-ID: 21326 | OA
Wu D, Mondelli M. Neural collapse beyond the unconstrained features model: Landscape, dynamics, and generalization in the mean-field regime. In: Proceedings of the 42nd International Conference on Machine Learning. Vol 267. ML Research Press; 2025:67499-67536.
[Published Version] View | Files available | arXiv
 

2025 | Published | Conference Paper | IST-REx-ID: 21328 | OA
Kovačević F, Yihan Z, Mondelli M. Spectral estimators for multi-index models: Precise asymptotics and optimal weak recovery. In: Proceedings of 38th Conference on Learning Theory. Vol 291. ML Research Press; 2025:3354-3404.
[Published Version] View | Files available | arXiv
 

2024 | Published | Journal Article | IST-REx-ID: 14665 | OA
Zhang Y, Vatedka S. Multiple packing: Lower bounds via error exponents. IEEE Transactions on Information Theory. 2024;70(2):1008-1039. doi:10.1109/TIT.2023.3334032
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 

2024 | Published | Conference Paper | IST-REx-ID: 17893 | OA
Jin L, Esposito AR, Gastpar M. Properties of the strong data processing constant for Rényi divergence. In: Proceedings of the 2024 IEEE International Symposium on Information Theory. Institute of Electrical and Electronics Engineers; 2024:3178-3183. doi:10.1109/ISIT57864.2024.10619367
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 

2024 | Published | Conference Paper | IST-REx-ID: 17894
Esposito AR, Gastpar M, Issa I. Variational characterizations of Sibson’s α-mutual information. In: Proceedings of the 2024 IEEE International Symposium on Information Theory . Institute of Electrical and Electronics Engineers; 2024:2110-2115. doi:10.1109/ISIT57864.2024.10619378
View | DOI | WoS
 

2024 | Published | Conference Paper | IST-REx-ID: 17895
Dey BK, Jaggi S, Langberg M, Sarwate AD, Zhang Y. Computationally efficient codes for strongly Dobrushin-Stambler nonsymmetrizable oblivious AVCs. In: Proceedings of the 2024 IEEE International Symposium on Information Theory . Institute of Electrical and Electronics Engineers; 2024:1586-1591. doi:10.1109/ISIT57864.2024.10619362
View | DOI | WoS
 

2024 | Published | Journal Article | IST-REx-ID: 18652
Dey BK, Jaggi S, Langberg M, Sarwate AD, Zhang Y. Codes for adversaries: Between worst-case and average-case jamming. Foundations and Trends in Communications and Information Theory. 2024;21(3-4):300-588. doi:10.1561/0100000112
View | DOI
 

2024 | Published | Conference Paper | IST-REx-ID: 18890 | OA
Beaglehole D, Súkeník P, Mondelli M, Belkin M. Average gradient outer product as a mechanism for deep neural collapse. In: 38th Annual Conference on Neural Information Processing Systems. Vol 37. Neural Information Processing Systems Foundation; 2024.
[Preprint] View | Download Preprint (ext.) | arXiv
 

Filters and Search Terms

department=MaMo

Search

Filter Publications

Display / Sort

Citation Style: AMA

Export / Embed