Prix Lopez-Loretta 2019 - Marco Mondelli
Project Period: 2020-10-01 – 2025-09-30
Externally Funded
Principal Investigator
Marco Mondelli
Department(s)
Mondelli Group
Funder
Fondation_Lopez_Loreta
25 Publications
2024 |In Press| Journal Article | IST-REx-ID: 15172
Concentration without independence via information measures
A.R. Esposito, M. Mondelli, IEEE Transactions on Information Theory (n.d.).
View
| Files available
| DOI
| arXiv
A.R. Esposito, M. Mondelli, IEEE Transactions on Information Theory (n.d.).
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
A. Depope, M. Mondelli, M.R. Robinson, in:, 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, 2024, pp. 13151–13155.
2023 |Published| Journal Article | IST-REx-ID: 13315 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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
J. Barbier, F. Camilli, M. Mondelli, M. Sáenz, Proceedings of the National Academy of Sciences of the United States of America 120 (2023).
2023 |Published| Conference Paper | IST-REx-ID: 14459 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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
| Download Preprint (ext.)
| arXiv
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.
2023 |Published| Conference Paper | IST-REx-ID: 13321 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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
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.
2023 |Published| Conference Paper | IST-REx-ID: 12859 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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
S. Bombari, S. Kiyani, M. Mondelli, in:, Proceedings of the 40th International Conference on Machine Learning, ML Research Press, 2023, pp. 2738–2776.
2023 |In Press| Conference Paper | IST-REx-ID: 14921 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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, n.d.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
P. Súkeník, M. Mondelli, C. Lampert, in:, 37th Annual Conference on Neural Information Processing Systems, n.d.
2023 |Published| Conference Paper | IST-REx-ID: 14924 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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
D. Wu, V. Kungurtsev, M. Mondelli, in:, Transactions on Machine Learning Research, ML Research Press, 2023.
2023 |Published| Conference Paper | IST-REx-ID: 14922 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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
A.R. Esposito, M. Mondelli, in:, Proceedings of 2023 IEEE International Symposium on Information Theory, IEEE, 2023, pp. 400–405.
2022 |Published| Journal Article | IST-REx-ID: 11420 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Mean-field analysis of piecewise linear solutions for wide ReLU networks
A. Shevchenko, V. Kungurtsev, M. Mondelli, Journal of Machine Learning Research 23 (2022) 1–55.
[Published Version]
View
| Files available
| arXiv
A. Shevchenko, V. Kungurtsev, M. Mondelli, Journal of Machine Learning Research 23 (2022) 1–55.
2022 |Published| Conference Paper | IST-REx-ID: 12016 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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
D. Fathollahi, M. Mondelli, in:, 2022 IEEE International Symposium on Information Theory, IEEE, 2022, pp. 2154–2159.
2022 |Published| Conference Paper | IST-REx-ID: 12540 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Estimation in rotationally invariant generalized linear models via approximate message passing
R. Venkataramanan, K. Kögler, M. Mondelli, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, 2022.
[Published Version]
View
| Files available
R. Venkataramanan, K. Kögler, M. Mondelli, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, 2022.
2022 |Published| Journal Article | IST-REx-ID: 10364 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
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
S.A. Hashemi, M. Mondelli, A. Fazeli, A. Vardy, J. Cioffi, A. Goldsmith, IEEE Transactions on Wireless Communications 21 (2022) 3909–3920.
2022 |Published| Conference Paper | IST-REx-ID: 12537 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Memorization and optimization in deep neural networks with minimum over-parameterization
S. Bombari, M.H. Amani, M. Mondelli, in:, 36th Conference on Neural Information Processing Systems, Curran Associates, 2022, pp. 7628–7640.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
S. Bombari, M.H. Amani, M. Mondelli, in:, 36th Conference on Neural Information Processing Systems, Curran Associates, 2022, pp. 7628–7640.
2022 |Published| Journal Article | IST-REx-ID: 12480 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Approximate message passing with spectral initialization for generalized linear models
M. Mondelli, R. Venkataramanan, Journal of Statistical Mechanics: Theory and Experiment 2022 (2022).
[Published Version]
View
| Files available
| DOI
| WoS
M. Mondelli, R. Venkataramanan, Journal of Statistical Mechanics: Theory and Experiment 2022 (2022).
2021 |Published| Conference Paper | IST-REx-ID: 10595 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep ReLU networks
Q. Nguyen, M. Mondelli, G.F. Montufar, in:, M. Meila, T. Zhang (Eds.), Proceedings of the 38th International Conference on Machine Learning, ML Research Press, 2021, pp. 8119–8129.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
Q. Nguyen, M. Mondelli, G.F. Montufar, in:, M. Meila, T. Zhang (Eds.), Proceedings of the 38th International Conference on Machine Learning, ML Research Press, 2021, pp. 8119–8129.
2021 |Published| Conference Paper | IST-REx-ID: 10599 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Successive syndrome-check decoding of polar codes
S.A. Hashemi, M. Mondelli, J. Cioffi, A. Goldsmith, in:, Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, Institute of Electrical and Electronics Engineers, 2021, pp. 943–947.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
S.A. Hashemi, M. Mondelli, J. Cioffi, A. Goldsmith, in:, Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, Institute of Electrical and Electronics Engineers, 2021, pp. 943–947.
2021 |Published| Conference Paper | IST-REx-ID: 13146 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Tight bounds on the smallest Eigenvalue of the neural tangent kernel for deep ReLU networks
Q. Nguyen, M. Mondelli, G. Montufar, in:, Proceedings of the 38th International Conference on Machine Learning, ML Research Press, 2021, pp. 8119–8129.
[Published Version]
View
| Files available
| arXiv
Q. Nguyen, M. Mondelli, G. Montufar, in:, Proceedings of the 38th International Conference on Machine Learning, ML Research Press, 2021, pp. 8119–8129.
2021 |Published| Conference Paper | IST-REx-ID: 10053 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Parallelism versus latency in simplified successive-cancellation decoding of polar codes
S.A. Hashemi, M. Mondelli, A. Fazeli, A. Vardy, J. Cioffi, A. Goldsmith, in:, 2021 IEEE International Symposium on Information Theory, Institute of Electrical and Electronics Engineers, 2021, pp. 2369–2374.
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
S.A. Hashemi, M. Mondelli, A. Fazeli, A. Vardy, J. Cioffi, A. Goldsmith, in:, 2021 IEEE International Symposium on Information Theory, Institute of Electrical and Electronics Engineers, 2021, pp. 2369–2374.
2021 |Published| Conference Paper | IST-REx-ID: 10597 |
![Open access file OA](https://research-explorer.ista.ac.at/images/access_open.png)
Sparse multi-decoder recursive projection aggregation for Reed-Muller codes
D. Fathollahi, N. Farsad, S.A. Hashemi, M. Mondelli, in:, 2021 IEEE International Symposium on Information Theory, Institute of Electrical and Electronics Engineers, 2021, pp. 1082–1087.
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
D. Fathollahi, N. Farsad, S.A. Hashemi, M. Mondelli, in:, 2021 IEEE International Symposium on Information Theory, Institute of Electrical and Electronics Engineers, 2021, pp. 1082–1087.