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
- 1 (current)
- 2
- 3
- 4
- 5
2025 |
Published |
Conference Paper |
IST-REx-ID: 20033 |
M. Emrullah Ildiz, H. A. Gozeten, E. O. Taga, M. Mondelli, and S. Oymak, “High-dimensional analysis of knowledge distillation: Weak-to-Strong generalization and scaling laws,” in 13th International Conference on Learning Representations, Singapore, Singapore, 2025, pp. 2967–3006.
[Published Version]
View
| Files available
| arXiv
2025 |
Published |
Conference Paper |
IST-REx-ID: 20035 |
A. Jacot, P. Súkeník, Z. Wang, and M. Mondelli, “Wide neural networks trained with weight decay provably exhibit neural collapse,” in 13th International Conference on Learning Representations, Singapore, Singapore, 2025, pp. 1905–1931.
[Published Version]
View
| Files available
| arXiv
2025 |
Epub ahead of print |
Journal Article |
IST-REx-ID: 20081 |
A. R. Esposito, M. Gastpar, and I. Issa, “Sibson α-mutual information and its variational representations,” IEEE Transactions on Information Theory. IEEE, 2025.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2025 |
Published |
Conference Paper |
IST-REx-ID: 20300 |
T. Wegel, F. Kovačević, A. Ţifrea, and F. Yang, “Learning Pareto manifolds in high dimensions: How can regularization help?,” in The 28th International Conference on Artificial Intelligence and Statistics, Mai Khao, Thailand, 2025, vol. 258, pp. 4591–4599.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2025 |
Published |
Conference Paper |
IST-REx-ID: 20667
A. El Latif Kadry, Y. Zhang, and N. Weinberger, “Mean estimation in high-dimensional binary timeinhomogeneous Markov Gaussian mixture models,” in 2025 IEEE International Symposium on Information Theory Proceedings, Ann Arbor, MI, United States, 2025.
View
| DOI
2025 |
Published |
Journal Article |
IST-REx-ID: 20734 |
|
|
Y. Zhang, H. C. Ji, R. Venkataramanan, and M. Mondelli, “Spectral estimators for structured generalized linear models via approximate message passing,” Mathematical Statistics and Learning, vol. 8, no. 3–4. EMS Press, pp. 193–304, 2025.
[Published Version]
View
| Files available
| DOI
2025 |
Published |
Journal Article |
IST-REx-ID: 18986 |
J. Barbier, F. Camilli, Y. Xu, and M. Mondelli, “Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise,” Physical Review Research, vol. 7. American Physical Society, 2025.
[Published Version]
View
| Files available
| DOI
| arXiv
2025 |
Published |
Journal Article |
IST-REx-ID: 19065 |
|
|
M. Fornasier, T. Klock, M. Mondelli, and M. Rauchensteiner, “Efficient identification of wide shallow neural networks with biases,” Applied and Computational Harmonic Analysis, vol. 77. Elsevier, 2025.
[Published Version]
View
| Files available
| DOI
| WoS
2025 |
Published |
Conference Paper |
IST-REx-ID: 19281 |
N. Resch, C. Yuan, and Y. Zhang, “Tight bounds on list-decodable and list-recoverable zero-rate codes,” in 16th Innovations in Theoretical Computer Science Conference, New York, NY, United States, 2025, vol. 325.
[Published Version]
View
| Files available
| DOI
| WoS
| arXiv
2025 |
Published |
Journal Article |
IST-REx-ID: 19627 |
S. Bombari and M. Mondelli, “Privacy for free in the overparameterized regime,” Proceedings of the National Academy of Sciences, vol. 122, no. 15. National Academy of Sciences, 2025.
[Published Version]
View
| Files available
| DOI
| WoS
| PubMed | Europe PMC
| arXiv
2025 |
Published |
Conference Paper |
IST-REx-ID: 21324 |
S. Bombari and M. Mondelli, “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, Vancouver, Canada, 2025, vol. 267, pp. 4839–4873.
[Published Version]
View
| Files available
| arXiv
2025 |
Published |
Conference Paper |
IST-REx-ID: 21325 |
H. A. Gozeten, M. E. Ildiz, X. Zhang, M. Soltanolkotabi, M. Mondelli, and S. Oymak, “Test-time training provably improves transformers as in-context learners,” in Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, 2025, vol. 267, pp. 20266–20295.
[Published Version]
View
| Files available
| PubMed | Europe PMC
2025 |
Published |
Conference Paper |
IST-REx-ID: 21326 |
D. Wu and M. Mondelli, “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, Vancouver, Canada, 2025, vol. 267, pp. 67499–67536.
[Published Version]
View
| Files available
| arXiv
2025 |
Published |
Conference Paper |
IST-REx-ID: 21328 |
F. Kovačević, Z. Yihan, and M. Mondelli, “Spectral estimators for multi-index models: Precise asymptotics and optimal weak recovery,” in Proceedings of 38th Conference on Learning Theory, Lyon, France, 2025, vol. 291, pp. 3354–3404.
[Published Version]
View
| Files available
| arXiv
2024 |
Published |
Journal Article |
IST-REx-ID: 14665 |
Y. Zhang and S. Vatedka, “Multiple packing: Lower bounds via error exponents,” IEEE Transactions on Information Theory, vol. 70, no. 2. IEEE, pp. 1008–1039, 2024.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2024 |
Published |
Conference Paper |
IST-REx-ID: 17893 |
L. Jin, A. R. Esposito, and M. Gastpar, “Properties of the strong data processing constant for Rényi divergence,” in Proceedings of the 2024 IEEE International Symposium on Information Theory, Athens, Greece, 2024, pp. 3178–3183.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2024 |
Published |
Conference Paper |
IST-REx-ID: 17895
B. K. Dey, S. Jaggi, M. Langberg, A. D. Sarwate, and Y. Zhang, “Computationally efficient codes for strongly Dobrushin-Stambler nonsymmetrizable oblivious AVCs,” in Proceedings of the 2024 IEEE International Symposium on Information Theory , Athens, Greece, 2024, pp. 1586–1591.
View
| DOI
| WoS
2024 |
Published |
Journal Article |
IST-REx-ID: 18652
B. K. Dey, S. Jaggi, M. Langberg, A. D. Sarwate, and Y. Zhang, “Codes for adversaries: Between worst-case and average-case jamming,” Foundations and Trends in Communications and Information Theory, vol. 21, no. 3–4. Now Publishers, pp. 300–588, 2024.
View
| DOI
2024 |
Published |
Conference Paper |
IST-REx-ID: 18890 |
D. Beaglehole, P. Súkeník, M. Mondelli, and M. Belkin, “Average gradient outer product as a mechanism for deep neural collapse,” in 38th Annual Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
- 1 (current)
- 2
- 3
- 4
- 5