Prix Lopez-Loretta 2019 - Marco Mondelli

Project Period: 2020-10-01 – 2025-09-30
Funder: Fondation_Lopez_Loreta
Principal Investigator
Department(s)
Mondelli Group
Funder
Fondation_Lopez_Loreta

34 Publications

2025 | Published | Journal Article | IST-REx-ID: 18986 | OA
Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise
J. Barbier, F. Camilli, Y. Xu, M. Mondelli, Physical Review Research 7 (2025).
[Published Version] View | Files available | DOI | arXiv
 
2024 | Published | Conference Paper | IST-REx-ID: 18897 | OA
Improved convergence of score-based diffusion models via prediction-correction
F. Pedrotti, J. Maas, M. Mondelli, in:, Transactions on Machine Learning Research, 2024.
[Published Version] View | Files available | arXiv
 
2024 | Draft | Preprint | IST-REx-ID: 17350 | OA
Improved convergence of score-based diffusion models via prediction-correction
F. Pedrotti, J. Maas, M. Mondelli, ArXiv (n.d.).
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
2024 | Published | Conference Paper | IST-REx-ID: 18973 | OA
Towards understanding the word sensitivity of attention layers: A study via random features
S. Bombari, M. Mondelli, in:, 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 4300–4328.
[Preprint] View | Download Preprint (ext.) | arXiv
 
2024 | Published | Conference Paper | IST-REx-ID: 18972 | OA
How spurious features are memorized: Precise analysis for random and NTK features
S. Bombari, M. Mondelli, in:, 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 4267–4299.
[Preprint] View | Download Preprint (ext.) | arXiv
 
2024 | Published | Conference Paper | IST-REx-ID: 18891 | OA
Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?
P. Súkeník, C. Lampert, M. Mondelli, in:, 38th Annual Conference on Neural Information Processing Systems, Curran Associates, 2024.
[Published Version] View | Files available
 
2024 | Published | Conference Paper | IST-REx-ID: 18890 | OA
Average gradient outer product as a mechanism for deep neural collapse
D. Beaglehole, P. Súkeník, M. Mondelli, M. Belkin, in:, 38th Annual Conference on Neural Information Processing Systems, Curran Associates, 2024.
[Preprint] View | Download Preprint (ext.) | arXiv
 
2024 | Published | Conference Paper | IST-REx-ID: 17147
Inference of genetic effects via approximate message passing
A. Depope, M. Mondelli, M.R. Robinson, in:, 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, 2024, pp. 13151–13155.
View | DOI
 
2024 | Published | Journal Article | IST-REx-ID: 15172 | OA
Concentration without independence via information measures
A.R. Esposito, M. Mondelli, IEEE Transactions on Information Theory 70 (2024) 3823–3839.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
2024 | Published | Thesis | IST-REx-ID: 17465 | OA
High-dimensional limits in artificial neural networks
A. Shevchenko, High-Dimensional Limits in Artificial Neural Networks, Institute of Science and Technology Austria, 2024.
[Published Version] View | Files available | DOI
 
2024 | Published | Conference Paper | IST-REx-ID: 17469 | OA
Compression of structured data with autoencoders: Provable benefit of nonlinearities and depth
K. Kögler, A. Shevchenko, H. Hassani, M. Mondelli, in:, Proceedings of the 41st International Conference on Machine Learning, ML Research Press, 2024, pp. 24964–25015.
[Published Version] View | Files available | Download Published Version (ext.) | arXiv
 
2023 | Published | Journal Article | IST-REx-ID: 13315 | OA
Fundamental limits in structured principal component analysis and how to reach them
J. Barbier, F. Camilli, M. Mondelli, M. Sáenz, Proceedings of the National Academy of Sciences of the United States of America 120 (2023).
[Published Version] View | Files available | DOI | PubMed | Europe PMC
 
2023 | Published | Conference Paper | IST-REx-ID: 13321 | OA
Approximate message passing for multi-layer estimation in rotationally invariant models
Y. Xu, T.Q. Hou, S.S. Liang, M. Mondelli, in:, 2023 IEEE Information Theory Workshop, Institute of Electrical and Electronics Engineers, 2023, pp. 294–298.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 12859 | OA
Beyond the universal law of robustness: Sharper laws for random features and neural tangent kernels
S. Bombari, S. Kiyani, M. Mondelli, in:, Proceedings of the 40th International Conference on Machine Learning, ML Research Press, 2023, pp. 2738–2776.
[Preprint] View | Files available | Download Preprint (ext.) | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 14921 | OA
Deep neural collapse is provably optimal for the deep unconstrained features model
P. Súkeník, M. Mondelli, C. Lampert, in:, 37th Annual Conference on Neural Information Processing Systems, 2023.
[Preprint] View | Download Preprint (ext.) | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 14922 | OA
Concentration without independence via information measures
A.R. Esposito, M. Mondelli, in:, Proceedings of 2023 IEEE International Symposium on Information Theory, IEEE, 2023, pp. 400–405.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 14924 | OA
Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
D. Wu, V. Kungurtsev, M. Mondelli, in:, Transactions on Machine Learning Research, ML Research Press, 2023.
[Published Version] View | Download Published Version (ext.) | arXiv
 
2023 | Published | Conference Paper | IST-REx-ID: 14459 | OA
Fundamental limits of two-layer autoencoders, and achieving them with gradient methods
A. Shevchenko, K. Kögler, H. Hassani, M. Mondelli, in:, Proceedings of the 40th International Conference on Machine Learning, ML Research Press, 2023, pp. 31151–31209.
[Preprint] View | Files available | Download Preprint (ext.) | arXiv
 
2022 | Published | Journal Article | IST-REx-ID: 10364 | OA
Parallelism versus latency in simplified successive-cancellation decoding of polar codes
S.A. Hashemi, M. Mondelli, A. Fazeli, A. Vardy, J. Cioffi, A. Goldsmith, IEEE Transactions on Wireless Communications 21 (2022) 3909–3920.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | WoS | arXiv
 
2022 | Published | Conference Paper | IST-REx-ID: 12016 | OA
Polar coded computing: The role of the scaling exponent
D. Fathollahi, M. Mondelli, in:, 2022 IEEE International Symposium on Information Theory, IEEE, 2022, pp. 2154–2159.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 

Search

Filter Publications

Display / Sort

Export / Embed