Marco Mondelli

Mondelli Group

60 Publications

Mark all

[60]
2024 | Journal Article | IST-REx-ID: 15172
A. R. Esposito and M. Mondelli, “Concentration without independence via information measures,” IEEE Transactions on Information Theory. IEEE.
View | Files available | DOI | arXiv
 
[59]
2023 | Journal Article | IST-REx-ID: 13315 | OA
J. Barbier, F. Camilli, M. Mondelli, and M. Sáenz, “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, vol. 120, no. 30. National Academy of Sciences, 2023.
[Published Version] View | Files available | DOI | PubMed | Europe PMC
 
[58]
2023 | Conference Paper | IST-REx-ID: 14459 | OA
A. Shevchenko, K. Kögler, H. Hassani, and M. Mondelli, “Fundamental limits of two-layer autoencoders, and achieving them with gradient methods,” in Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, HI, United States, 2023, vol. 202, pp. 31151–31209.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[57]
2023 | Conference Paper | IST-REx-ID: 13321 | OA
Y. Xu, T. Q. Hou, S. S. Liang, and M. Mondelli, “Approximate message passing for multi-layer estimation in rotationally invariant models,” in 2023 IEEE Information Theory Workshop, Saint-Malo, France, 2023, pp. 294–298.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
[56]
2023 | Conference Paper | IST-REx-ID: 12859 | OA
S. Bombari, S. Kiyani, and M. Mondelli, “Beyond the universal law of robustness: Sharper laws for random features and neural tangent kernels,” in Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, United States, 2023, vol. 202, pp. 2738–2776.
[Preprint] View | Files available | Download Preprint (ext.) | arXiv
 
[55]
2023 | Conference Paper | IST-REx-ID: 14921 | OA
P. Súkeník, M. Mondelli, and C. Lampert, “Deep neural collapse is provably optimal for the deep unconstrained features model,” in 37th Annual Conference on Neural Information Processing Systems, New Orleans, LA, United States.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[54]
2023 | Conference Paper | IST-REx-ID: 14924 | OA
D. Wu, V. Kungurtsev, and M. Mondelli, “Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence,” in Transactions on Machine Learning Research, 2023.
[Published Version] View | Download Published Version (ext.) | arXiv
 
[53]
2023 | Conference Paper | IST-REx-ID: 14923 | OA
T. Fu, Y. Liu, J. Barbier, M. Mondelli, S. Liang, and T. Hou, “Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise,” in Proceedings of 2023 IEEE International Symposium on Information Theory, Taipei, Taiwan.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[52]
2023 | Conference Paper | IST-REx-ID: 14922 | OA
A. R. Esposito and M. Mondelli, “Concentration without independence via information measures,” in Proceedings of 2023 IEEE International Symposium on Information Theory, Taipei, Taiwan, 2023, pp. 400–405.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[51]
2022 | Journal Article | IST-REx-ID: 11420 | OA
A. Shevchenko, V. Kungurtsev, and M. Mondelli, “Mean-field analysis of piecewise linear solutions for wide ReLU networks,” Journal of Machine Learning Research, vol. 23, no. 130. Journal of Machine Learning Research, pp. 1–55, 2022.
[Published Version] View | Files available | arXiv
 
[50]
2022 | Conference Paper | IST-REx-ID: 12016 | OA
D. Fathollahi and M. Mondelli, “Polar coded computing: The role of the scaling exponent,” in 2022 IEEE International Symposium on Information Theory, Espoo, Finland, 2022, vol. 2022, pp. 2154–2159.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[49]
2022 | Conference Paper | IST-REx-ID: 12540 | OA
R. Venkataramanan, K. Kögler, and M. Mondelli, “Estimation in rotationally invariant generalized linear models via approximate message passing,” in Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, United States, 2022, vol. 162.
[Published Version] View | Files available
 
[48]
2022 | Preprint | IST-REx-ID: 12536 | OA
J. Barbier, T. Hou, M. Mondelli, and M. Saenz, “The price of ignorance: How much does it cost to forget noise structure in low-rank matrix estimation?,” arXiv. .
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[47]
2022 | Journal Article | IST-REx-ID: 12233 | OA
N. Doan, S. A. Hashemi, M. Mondelli, and W. J. Gross, “Decoding Reed-Muller codes with successive codeword permutations,” IEEE Transactions on Communications, vol. 70, no. 11. Institute of Electrical and Electronics Engineers, pp. 7134–7145, 2022.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
[46]
2022 | Journal Article | IST-REx-ID: 10364 | OA
S. A. Hashemi, M. Mondelli, A. Fazeli, A. Vardy, J. Cioffi, and A. Goldsmith, “Parallelism versus latency in simplified successive-cancellation decoding of polar codes,” IEEE Transactions on Wireless Communications, vol. 21, no. 6. Institute of Electrical and Electronics Engineers, pp. 3909–3920, 2022.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | WoS | arXiv
 
[45]
2022 | Journal Article | IST-REx-ID: 12538 | OA
M. H. Amani, S. Bombari, M. Mondelli, R. Pukdee, and S. Rini, “Sharp asymptotics on the compression of two-layer neural networks,” IEEE Information Theory Workshop. IEEE, pp. 588–593, 2022.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[44]
2022 | Conference Paper | IST-REx-ID: 12537 | OA
S. Bombari, M. H. Amani, and M. Mondelli, “Memorization and optimization in deep neural networks with minimum over-parameterization,” in 36th Conference on Neural Information Processing Systems, 2022, vol. 35, pp. 7628–7640.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[43]
2022 | Journal Article | IST-REx-ID: 12480 | OA
M. Mondelli and R. Venkataramanan, “Approximate message passing with spectral initialization for generalized linear models,” Journal of Statistical Mechanics: Theory and Experiment, vol. 2022, no. 11. IOP Publishing, 2022.
[Published Version] View | Files available | DOI | WoS
 
[42]
2021 | Conference Paper | IST-REx-ID: 10595 | OA
Q. Nguyen, M. Mondelli, and G. F. Montufar, “Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep ReLU networks,” in Proceedings of the 38th International Conference on Machine Learning, Virtual, 2021, vol. 139, pp. 8119–8129.
[Published Version] View | Download Published Version (ext.) | arXiv
 
[41]
2021 | Conference Paper | IST-REx-ID: 10599 | OA
S. A. Hashemi, M. Mondelli, J. Cioffi, and A. Goldsmith, “Successive syndrome-check decoding of polar codes,” in Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, Virtual, Pacific Grove, CA, United States, 2021, vol. 2021–October, pp. 943–947.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[40]
2021 | Conference Paper | IST-REx-ID: 13146 | OA
Q. Nguyen, M. Mondelli, and G. Montufar, “Tight bounds on the smallest Eigenvalue of the neural tangent kernel for deep ReLU networks,” in Proceedings of the 38th International Conference on Machine Learning, Virtual, 2021, vol. 139, pp. 8119–8129.
[Published Version] View | Files available | arXiv
 
[39]
2021 | Journal Article | IST-REx-ID: 9047 | OA
M. Mondelli, S. A. Hashemi, J. M. Cioffi, and A. Goldsmith, “Sublinear latency for simplified successive cancellation decoding of polar codes,” IEEE Transactions on Wireless Communications, vol. 20, no. 1. IEEE, pp. 18–27, 2021.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | WoS | arXiv
 
[38]
2021 | Conference Paper | IST-REx-ID: 10053 | OA
S. A. Hashemi, M. Mondelli, A. Fazeli, A. Vardy, J. Cioffi, and A. Goldsmith, “Parallelism versus latency in simplified successive-cancellation decoding of polar codes,” in 2021 IEEE International Symposium on Information Theory, Melbourne, Australia, 2021, pp. 2369–2374.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | WoS | arXiv
 
[37]
2021 | Conference Paper | IST-REx-ID: 10597 | OA
D. Fathollahi, N. Farsad, S. A. Hashemi, and M. Mondelli, “Sparse multi-decoder recursive projection aggregation for Reed-Muller codes,” in 2021 IEEE International Symposium on Information Theory, Virtual, Melbourne, Australia, 2021, pp. 1082–1087.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
[36]
2021 | Journal Article | IST-REx-ID: 10211 | OA
M. Mondelli, C. Thrampoulidis, and R. Venkataramanan, “Optimal combination of linear and spectral estimators for generalized linear models,” Foundations of Computational Mathematics. Springer, 2021.
[Published Version] View | Files available | DOI | WoS | arXiv
 
[35]
2021 | Conference Paper | IST-REx-ID: 10593 | OA
M. Mondelli and R. Venkataramanan, “PCA initialization for approximate message passing in rotationally invariant models,” in 35th Conference on Neural Information Processing Systems, Virtual, 2021, vol. 35, pp. 29616–29629.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[34]
2021 | Conference Paper | IST-REx-ID: 10594 | OA
Q. Nguyen, P. Bréchet, and M. Mondelli, “When are solutions connected in deep networks?,” in 35th Conference on Neural Information Processing Systems, Virtual, 2021, vol. 35.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[33]
2021 | Conference Paper | IST-REx-ID: 10598 | OA
M. Mondelli and R. Venkataramanan, “Approximate message passing with spectral initialization for generalized linear models,” in Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, Virtual, San Diego, CA, United States, 2021, vol. 130, pp. 397–405.
[Preprint] View | Files available | Download Preprint (ext.) | arXiv
 
[32]
2021 | Journal Article | IST-REx-ID: 9002
A. Fazeli, H. Hassani, M. Mondelli, and A. Vardy, “Binary linear codes with optimal scaling: Polar codes with large kernels,” IEEE Transactions on Information Theory, vol. 67, no. 9. IEEE, pp. 5693–5710, 2021.
[Preprint] View | Files available | DOI | arXiv
 
[31]
2020 | Conference Paper | IST-REx-ID: 9221 | OA
Q. Nguyen and M. Mondelli, “Global convergence of deep networks with one wide layer followed by pyramidal topology,” in 34th Conference on Neural Information Processing Systems, Vancouver, Canada, 2020, vol. 33, pp. 11961–11972.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[30]
2020 | Conference Paper | IST-REx-ID: 8536 | OA
M. Mondelli, S. A. Hashemi, J. Cioffi, and A. Goldsmith, “Simplified successive cancellation decoding of polar codes has sublinear latency,” in IEEE International Symposium on Information Theory - Proceedings, Los Angeles, CA, United States, 2020, vol. 2020–June.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[29]
2020 | Conference Paper | IST-REx-ID: 9198 | OA
A. Shevchenko and M. Mondelli, “Landscape connectivity and dropout stability of SGD solutions for over-parameterized neural networks,” in Proceedings of the 37th International Conference on Machine Learning, 2020, vol. 119, pp. 8773–8784.
[Published Version] View | Files available | arXiv
 
[28]
2020 | Journal Article | IST-REx-ID: 6748 | OA
A. Javanmard, M. Mondelli, and A. Montanari, “Analysis of a two-layer neural network via displacement convexity,” Annals of Statistics, vol. 48, no. 6. Institute of Mathematical Statistics, pp. 3619–3642, 2020.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
[27]
2019 | Journal Article | IST-REx-ID: 6662 | OA
M. Mondelli and A. Montanari, “Fundamental limits of weak recovery with applications to phase retrieval,” Foundations of Computational Mathematics, vol. 19, no. 3. Springer, pp. 703–773, 2019.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[26]
2019 | Journal Article | IST-REx-ID: 6663 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “Construction of polar codes with sublinear complexity,” IEEE, vol. 65, no. 5. IEEE, pp. 2782–2791, 2019.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[25]
2019 | Conference Paper | IST-REx-ID: 6747 | OA
M. Mondelli and A. Montanari, “On the connection between learning two-layers neural networks and tensor  decomposition,” in Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, Naha, Okinawa, Japan, 2019, vol. 89, pp. 1051–1060.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[24]
2019 | Journal Article | IST-REx-ID: 6750 | OA
S. A. Hashemi, C. Condo, M. Mondelli, and W. J. Gross, “Rate-flexible fast polar decoders,” IEEE Transactions on Signal Processing, vol. 67, no. 22. IEEE, 2019.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[23]
2019 | Journal Article | IST-REx-ID: 7007 | OA
M. Mondelli, S. H. Hassani, and R. Urbanke, “A new coding paradigm for the primitive relay channel,” Algorithms, vol. 12, no. 10. MDPI, 2019.
[Published Version] View | Files available | DOI | arXiv
 
[22]
2018 | Conference Paper | IST-REx-ID: 6664 | OA
S. A. Hashemi, N. Doan, M. Mondelli, and W. Gross, “Decoding Reed-Muller and polar codes by successive factor graph permutations,” in 2018 IEEE 10th International Symposium on Turbo Codes & Iterative Information Processing, Hong Kong, China, 2018, pp. 1–5.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[21]
2018 | Journal Article | IST-REx-ID: 6674
S. A. Hashemi, M. Mondelli, S. H. Hassani, C. Condo, R. L. Urbanke, and W. J. Gross, “Decoder partitioning: Towards practical list decoding of polar codes,” IEEE Transactions on Communications, vol. 66, no. 9. IEEE, pp. 3749–3759, 2018.
View | DOI
 
[20]
2018 | Conference Paper | IST-REx-ID: 6728 | OA
N. Doan, S. A. Hashemi, M. Mondelli, and W. J. Gross, “On the decoding of polar codes on permuted factor graphs,” in 2018 IEEE Global Communications Conference , Abu Dhabi, United Arab Emirates, 2018.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[19]
2018 | Journal Article | IST-REx-ID: 6678 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “How to achieve the capacity of asymmetric channels,” IEEE Transactions on Information Theory, vol. 64, no. 5. IEEE, pp. 3371–3393, 2018.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[18]
2018 | Conference Paper | IST-REx-ID: 6675 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “A new coding paradigm for the primitive relay channel,” in 2018 IEEE International Symposium on Information Theory, Vail, CO, United States, 2018, pp. 351–355.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[17]
2018 | Conference Paper | IST-REx-ID: 6665 | OA
A. Fazeli, H. Hassani, M. Mondelli, and A. Vardy, “Binary linear codes with optimal scaling: Polar codes with large kernels,” in 2018 IEEE Information Theory Workshop, Guangzhou, China, 2018, pp. 1–5.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[16]
2017 | Conference Paper | IST-REx-ID: 6679 | OA
S. A. Hashemi, M. Mondelli, H. Hassani, R. Urbanke, and W. Gross, “Partitioned list decoding of polar codes: Analysis and improvement of finite length performance,” in 2017 IEEE Global Communications Conference, Singapore, Singapore, 2017, pp. 1–7.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[15]
2017 | Conference Paper | IST-REx-ID: 6729 | OA
M. Mondelli, S. H. Hassani, and R. Urbanke, “Construction of polar codes with sublinear complexity,” in 2017 IEEE International Symposium on Information Theory , Aachen, Germany, 2017, pp. 1853–1857.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[14]
2017 | Journal Article | IST-REx-ID: 6730 | OA
S. Kudekar, S. Kumar, M. Mondelli, H. D. Pfister, E. Sasoglu, and R. L. Urbanke, “Reed–Muller codes achieve capacity on erasure channels,” IEEE Transactions on Information Theory, vol. 63, no. 7. IEEE, pp. 4298–4316, 2017.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[13]
2017 | Conference Paper | IST-REx-ID: 6731 | OA
M. Mondelli, H. Hassani, I. Maric, D. Hui, and S.-N. Hong, “Capacity-achieving rate-compatible polar codes for general channels,” in 2017 IEEE Wireless Communications and Networking Conference Workshops , San Francisco, CA, USA, 2017.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[12]
2016 | Journal Article | IST-REx-ID: 6732 | OA
M. Mondelli, S. H. Hassani, and R. L. Urbanke, “Unified scaling of polar codes: Error exponent, scaling exponent, moderate deviations, and error floors,” IEEE Transactions on Information Theory, vol. 62, no. 12. IEEE, pp. 6698–6712, 2016.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[11]
2016 | Conference Paper | IST-REx-ID: 6733 | OA
S. Kudekar, S. Kumar, M. Mondelli, H. D. Pfister, and R. Urbankez, “Comparing the bit-MAP and block-MAP decoding thresholds of Reed-Muller codes on BMS channels,” in 2016 IEEE International Symposium on Information Theory , Barcelona, Spain, 2016, pp. 1755–1759.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[10]
2016 | Conference Paper | IST-REx-ID: 6770
M. Mondelli, S. Kudekar, S. Kumar, H. D. Pfister, E. Şaşoğlu, and R. Urbanke, “Reed-Muller codes: Thresholds and weight distribution,” in 24th International Zurich Seminar on Communications, Zurich, Switzerland, 2016, p. 50.
View | DOI
 
[9]
2015 | Journal Article | IST-REx-ID: 6737 | OA
M. Mondelli, H. Hassani, I. Sason, and R. Urbanke, “Achieving Marton’s region for broadcast channels using polar codes,” IEEE Transactions on Information Theory, vol. 61, no. 2. IEEE, pp. 783–800, 2015.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[8]
2015 | Journal Article | IST-REx-ID: 6736 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “Scaling exponent of list decoders with applications to polar codes,” IEEE Transactions on Information Theory, vol. 61, no. 9. IEEE, pp. 4838–4851, 2015.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[7]
2014 | Conference Paper | IST-REx-ID: 6740 | OA
M. Mondelli, R. Urbanke, and H. Hassani, “How to achieve the capacity of asymmetric channels,” in 52nd Annual Allerton Conference on Communication, Control, and Computing, Monticello, IL, United States, 2014, pp. 789–796.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[6]
2014 | Journal Article | IST-REx-ID: 6739 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “From polar to Reed-Muller codes: A technique to improve the finite-length performance,” IEEE Transactions on Communications, vol. 62, no. 9. IEEE, pp. 3084–3091, 2014.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[5]
2014 | Journal Article | IST-REx-ID: 6744
M. Mondelli, Q. Zhou, V. Lottici, and X. Ma, “Joint power allocation and path selection for multi-hop noncoherent decode and forward UWB communications,” IEEE Transactions on Wireless Communications, vol. 13, no. 3. IEEE, pp. 1397–1409, 2014.
View | DOI
 
[4]
2013 | Journal Article | IST-REx-ID: 6768 | OA
M. Mondelli, “A finite difference scheme for the stack filter simulating the MCM,” Image Processing On Line, vol. 3. Image Processing On Line, pp. 68–111, 2013.
[Published Version] View | Files available | DOI
 
[3]
2012 | Conference Paper | IST-REx-ID: 6746
M. Mondelli, Q. Zhou, X. Ma, and V. Lottici, “A cooperative approach for amplify-and-forward differential transmitted reference IR-UWB relay systems,” in 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, 2012, pp. 2905–2908.
View | DOI
 
[2]
2011 | Journal Article | IST-REx-ID: 6749 | OA
M. Mondelli and A. Ciomaga, “Finite difference schemes for MCM and AMSS,” Image Processing On Line, vol. 1. IPOL Image Processing On Line, pp. 127–177, 2011.
[Published Version] View | Files available | DOI
 
[1]
2011 | Conference Paper | IST-REx-ID: 6767
M. Mondelli and A. Ciomaga, “On finite difference schemes for curvature motions,” in Proceedings of the International Student Conference on Pure and Applied Mathematics, Iasi, Romania, 2011, pp. 137–156.
View | DOI
 
Marked Publication(s)

Search

Filter Publications

    • Display / Sort

    Citation Style: IEEE

    Export / Embed

60 Publications

Mark all

[60]
2024 | Journal Article | IST-REx-ID: 15172
A. R. Esposito and M. Mondelli, “Concentration without independence via information measures,” IEEE Transactions on Information Theory. IEEE.
View | Files available | DOI | arXiv
 
[59]
2023 | Journal Article | IST-REx-ID: 13315 | OA
J. Barbier, F. Camilli, M. Mondelli, and M. Sáenz, “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, vol. 120, no. 30. National Academy of Sciences, 2023.
[Published Version] View | Files available | DOI | PubMed | Europe PMC
 
[58]
2023 | Conference Paper | IST-REx-ID: 14459 | OA
A. Shevchenko, K. Kögler, H. Hassani, and M. Mondelli, “Fundamental limits of two-layer autoencoders, and achieving them with gradient methods,” in Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, HI, United States, 2023, vol. 202, pp. 31151–31209.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[57]
2023 | Conference Paper | IST-REx-ID: 13321 | OA
Y. Xu, T. Q. Hou, S. S. Liang, and M. Mondelli, “Approximate message passing for multi-layer estimation in rotationally invariant models,” in 2023 IEEE Information Theory Workshop, Saint-Malo, France, 2023, pp. 294–298.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
[56]
2023 | Conference Paper | IST-REx-ID: 12859 | OA
S. Bombari, S. Kiyani, and M. Mondelli, “Beyond the universal law of robustness: Sharper laws for random features and neural tangent kernels,” in Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, United States, 2023, vol. 202, pp. 2738–2776.
[Preprint] View | Files available | Download Preprint (ext.) | arXiv
 
[55]
2023 | Conference Paper | IST-REx-ID: 14921 | OA
P. Súkeník, M. Mondelli, and C. Lampert, “Deep neural collapse is provably optimal for the deep unconstrained features model,” in 37th Annual Conference on Neural Information Processing Systems, New Orleans, LA, United States.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[54]
2023 | Conference Paper | IST-REx-ID: 14924 | OA
D. Wu, V. Kungurtsev, and M. Mondelli, “Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence,” in Transactions on Machine Learning Research, 2023.
[Published Version] View | Download Published Version (ext.) | arXiv
 
[53]
2023 | Conference Paper | IST-REx-ID: 14923 | OA
T. Fu, Y. Liu, J. Barbier, M. Mondelli, S. Liang, and T. Hou, “Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise,” in Proceedings of 2023 IEEE International Symposium on Information Theory, Taipei, Taiwan.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[52]
2023 | Conference Paper | IST-REx-ID: 14922 | OA
A. R. Esposito and M. Mondelli, “Concentration without independence via information measures,” in Proceedings of 2023 IEEE International Symposium on Information Theory, Taipei, Taiwan, 2023, pp. 400–405.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[51]
2022 | Journal Article | IST-REx-ID: 11420 | OA
A. Shevchenko, V. Kungurtsev, and M. Mondelli, “Mean-field analysis of piecewise linear solutions for wide ReLU networks,” Journal of Machine Learning Research, vol. 23, no. 130. Journal of Machine Learning Research, pp. 1–55, 2022.
[Published Version] View | Files available | arXiv
 
[50]
2022 | Conference Paper | IST-REx-ID: 12016 | OA
D. Fathollahi and M. Mondelli, “Polar coded computing: The role of the scaling exponent,” in 2022 IEEE International Symposium on Information Theory, Espoo, Finland, 2022, vol. 2022, pp. 2154–2159.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[49]
2022 | Conference Paper | IST-REx-ID: 12540 | OA
R. Venkataramanan, K. Kögler, and M. Mondelli, “Estimation in rotationally invariant generalized linear models via approximate message passing,” in Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, United States, 2022, vol. 162.
[Published Version] View | Files available
 
[48]
2022 | Preprint | IST-REx-ID: 12536 | OA
J. Barbier, T. Hou, M. Mondelli, and M. Saenz, “The price of ignorance: How much does it cost to forget noise structure in low-rank matrix estimation?,” arXiv. .
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[47]
2022 | Journal Article | IST-REx-ID: 12233 | OA
N. Doan, S. A. Hashemi, M. Mondelli, and W. J. Gross, “Decoding Reed-Muller codes with successive codeword permutations,” IEEE Transactions on Communications, vol. 70, no. 11. Institute of Electrical and Electronics Engineers, pp. 7134–7145, 2022.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
[46]
2022 | Journal Article | IST-REx-ID: 10364 | OA
S. A. Hashemi, M. Mondelli, A. Fazeli, A. Vardy, J. Cioffi, and A. Goldsmith, “Parallelism versus latency in simplified successive-cancellation decoding of polar codes,” IEEE Transactions on Wireless Communications, vol. 21, no. 6. Institute of Electrical and Electronics Engineers, pp. 3909–3920, 2022.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | WoS | arXiv
 
[45]
2022 | Journal Article | IST-REx-ID: 12538 | OA
M. H. Amani, S. Bombari, M. Mondelli, R. Pukdee, and S. Rini, “Sharp asymptotics on the compression of two-layer neural networks,” IEEE Information Theory Workshop. IEEE, pp. 588–593, 2022.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[44]
2022 | Conference Paper | IST-REx-ID: 12537 | OA
S. Bombari, M. H. Amani, and M. Mondelli, “Memorization and optimization in deep neural networks with minimum over-parameterization,” in 36th Conference on Neural Information Processing Systems, 2022, vol. 35, pp. 7628–7640.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[43]
2022 | Journal Article | IST-REx-ID: 12480 | OA
M. Mondelli and R. Venkataramanan, “Approximate message passing with spectral initialization for generalized linear models,” Journal of Statistical Mechanics: Theory and Experiment, vol. 2022, no. 11. IOP Publishing, 2022.
[Published Version] View | Files available | DOI | WoS
 
[42]
2021 | Conference Paper | IST-REx-ID: 10595 | OA
Q. Nguyen, M. Mondelli, and G. F. Montufar, “Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep ReLU networks,” in Proceedings of the 38th International Conference on Machine Learning, Virtual, 2021, vol. 139, pp. 8119–8129.
[Published Version] View | Download Published Version (ext.) | arXiv
 
[41]
2021 | Conference Paper | IST-REx-ID: 10599 | OA
S. A. Hashemi, M. Mondelli, J. Cioffi, and A. Goldsmith, “Successive syndrome-check decoding of polar codes,” in Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, Virtual, Pacific Grove, CA, United States, 2021, vol. 2021–October, pp. 943–947.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[40]
2021 | Conference Paper | IST-REx-ID: 13146 | OA
Q. Nguyen, M. Mondelli, and G. Montufar, “Tight bounds on the smallest Eigenvalue of the neural tangent kernel for deep ReLU networks,” in Proceedings of the 38th International Conference on Machine Learning, Virtual, 2021, vol. 139, pp. 8119–8129.
[Published Version] View | Files available | arXiv
 
[39]
2021 | Journal Article | IST-REx-ID: 9047 | OA
M. Mondelli, S. A. Hashemi, J. M. Cioffi, and A. Goldsmith, “Sublinear latency for simplified successive cancellation decoding of polar codes,” IEEE Transactions on Wireless Communications, vol. 20, no. 1. IEEE, pp. 18–27, 2021.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | WoS | arXiv
 
[38]
2021 | Conference Paper | IST-REx-ID: 10053 | OA
S. A. Hashemi, M. Mondelli, A. Fazeli, A. Vardy, J. Cioffi, and A. Goldsmith, “Parallelism versus latency in simplified successive-cancellation decoding of polar codes,” in 2021 IEEE International Symposium on Information Theory, Melbourne, Australia, 2021, pp. 2369–2374.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | WoS | arXiv
 
[37]
2021 | Conference Paper | IST-REx-ID: 10597 | OA
D. Fathollahi, N. Farsad, S. A. Hashemi, and M. Mondelli, “Sparse multi-decoder recursive projection aggregation for Reed-Muller codes,” in 2021 IEEE International Symposium on Information Theory, Virtual, Melbourne, Australia, 2021, pp. 1082–1087.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
[36]
2021 | Journal Article | IST-REx-ID: 10211 | OA
M. Mondelli, C. Thrampoulidis, and R. Venkataramanan, “Optimal combination of linear and spectral estimators for generalized linear models,” Foundations of Computational Mathematics. Springer, 2021.
[Published Version] View | Files available | DOI | WoS | arXiv
 
[35]
2021 | Conference Paper | IST-REx-ID: 10593 | OA
M. Mondelli and R. Venkataramanan, “PCA initialization for approximate message passing in rotationally invariant models,” in 35th Conference on Neural Information Processing Systems, Virtual, 2021, vol. 35, pp. 29616–29629.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[34]
2021 | Conference Paper | IST-REx-ID: 10594 | OA
Q. Nguyen, P. Bréchet, and M. Mondelli, “When are solutions connected in deep networks?,” in 35th Conference on Neural Information Processing Systems, Virtual, 2021, vol. 35.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[33]
2021 | Conference Paper | IST-REx-ID: 10598 | OA
M. Mondelli and R. Venkataramanan, “Approximate message passing with spectral initialization for generalized linear models,” in Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, Virtual, San Diego, CA, United States, 2021, vol. 130, pp. 397–405.
[Preprint] View | Files available | Download Preprint (ext.) | arXiv
 
[32]
2021 | Journal Article | IST-REx-ID: 9002
A. Fazeli, H. Hassani, M. Mondelli, and A. Vardy, “Binary linear codes with optimal scaling: Polar codes with large kernels,” IEEE Transactions on Information Theory, vol. 67, no. 9. IEEE, pp. 5693–5710, 2021.
[Preprint] View | Files available | DOI | arXiv
 
[31]
2020 | Conference Paper | IST-REx-ID: 9221 | OA
Q. Nguyen and M. Mondelli, “Global convergence of deep networks with one wide layer followed by pyramidal topology,” in 34th Conference on Neural Information Processing Systems, Vancouver, Canada, 2020, vol. 33, pp. 11961–11972.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[30]
2020 | Conference Paper | IST-REx-ID: 8536 | OA
M. Mondelli, S. A. Hashemi, J. Cioffi, and A. Goldsmith, “Simplified successive cancellation decoding of polar codes has sublinear latency,” in IEEE International Symposium on Information Theory - Proceedings, Los Angeles, CA, United States, 2020, vol. 2020–June.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[29]
2020 | Conference Paper | IST-REx-ID: 9198 | OA
A. Shevchenko and M. Mondelli, “Landscape connectivity and dropout stability of SGD solutions for over-parameterized neural networks,” in Proceedings of the 37th International Conference on Machine Learning, 2020, vol. 119, pp. 8773–8784.
[Published Version] View | Files available | arXiv
 
[28]
2020 | Journal Article | IST-REx-ID: 6748 | OA
A. Javanmard, M. Mondelli, and A. Montanari, “Analysis of a two-layer neural network via displacement convexity,” Annals of Statistics, vol. 48, no. 6. Institute of Mathematical Statistics, pp. 3619–3642, 2020.
[Preprint] View | DOI | Download Preprint (ext.) | WoS | arXiv
 
[27]
2019 | Journal Article | IST-REx-ID: 6662 | OA
M. Mondelli and A. Montanari, “Fundamental limits of weak recovery with applications to phase retrieval,” Foundations of Computational Mathematics, vol. 19, no. 3. Springer, pp. 703–773, 2019.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[26]
2019 | Journal Article | IST-REx-ID: 6663 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “Construction of polar codes with sublinear complexity,” IEEE, vol. 65, no. 5. IEEE, pp. 2782–2791, 2019.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[25]
2019 | Conference Paper | IST-REx-ID: 6747 | OA
M. Mondelli and A. Montanari, “On the connection between learning two-layers neural networks and tensor  decomposition,” in Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, Naha, Okinawa, Japan, 2019, vol. 89, pp. 1051–1060.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[24]
2019 | Journal Article | IST-REx-ID: 6750 | OA
S. A. Hashemi, C. Condo, M. Mondelli, and W. J. Gross, “Rate-flexible fast polar decoders,” IEEE Transactions on Signal Processing, vol. 67, no. 22. IEEE, 2019.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[23]
2019 | Journal Article | IST-REx-ID: 7007 | OA
M. Mondelli, S. H. Hassani, and R. Urbanke, “A new coding paradigm for the primitive relay channel,” Algorithms, vol. 12, no. 10. MDPI, 2019.
[Published Version] View | Files available | DOI | arXiv
 
[22]
2018 | Conference Paper | IST-REx-ID: 6664 | OA
S. A. Hashemi, N. Doan, M. Mondelli, and W. Gross, “Decoding Reed-Muller and polar codes by successive factor graph permutations,” in 2018 IEEE 10th International Symposium on Turbo Codes & Iterative Information Processing, Hong Kong, China, 2018, pp. 1–5.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[21]
2018 | Journal Article | IST-REx-ID: 6674
S. A. Hashemi, M. Mondelli, S. H. Hassani, C. Condo, R. L. Urbanke, and W. J. Gross, “Decoder partitioning: Towards practical list decoding of polar codes,” IEEE Transactions on Communications, vol. 66, no. 9. IEEE, pp. 3749–3759, 2018.
View | DOI
 
[20]
2018 | Conference Paper | IST-REx-ID: 6728 | OA
N. Doan, S. A. Hashemi, M. Mondelli, and W. J. Gross, “On the decoding of polar codes on permuted factor graphs,” in 2018 IEEE Global Communications Conference , Abu Dhabi, United Arab Emirates, 2018.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[19]
2018 | Journal Article | IST-REx-ID: 6678 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “How to achieve the capacity of asymmetric channels,” IEEE Transactions on Information Theory, vol. 64, no. 5. IEEE, pp. 3371–3393, 2018.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[18]
2018 | Conference Paper | IST-REx-ID: 6675 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “A new coding paradigm for the primitive relay channel,” in 2018 IEEE International Symposium on Information Theory, Vail, CO, United States, 2018, pp. 351–355.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[17]
2018 | Conference Paper | IST-REx-ID: 6665 | OA
A. Fazeli, H. Hassani, M. Mondelli, and A. Vardy, “Binary linear codes with optimal scaling: Polar codes with large kernels,” in 2018 IEEE Information Theory Workshop, Guangzhou, China, 2018, pp. 1–5.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[16]
2017 | Conference Paper | IST-REx-ID: 6679 | OA
S. A. Hashemi, M. Mondelli, H. Hassani, R. Urbanke, and W. Gross, “Partitioned list decoding of polar codes: Analysis and improvement of finite length performance,” in 2017 IEEE Global Communications Conference, Singapore, Singapore, 2017, pp. 1–7.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[15]
2017 | Conference Paper | IST-REx-ID: 6729 | OA
M. Mondelli, S. H. Hassani, and R. Urbanke, “Construction of polar codes with sublinear complexity,” in 2017 IEEE International Symposium on Information Theory , Aachen, Germany, 2017, pp. 1853–1857.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[14]
2017 | Journal Article | IST-REx-ID: 6730 | OA
S. Kudekar, S. Kumar, M. Mondelli, H. D. Pfister, E. Sasoglu, and R. L. Urbanke, “Reed–Muller codes achieve capacity on erasure channels,” IEEE Transactions on Information Theory, vol. 63, no. 7. IEEE, pp. 4298–4316, 2017.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[13]
2017 | Conference Paper | IST-REx-ID: 6731 | OA
M. Mondelli, H. Hassani, I. Maric, D. Hui, and S.-N. Hong, “Capacity-achieving rate-compatible polar codes for general channels,” in 2017 IEEE Wireless Communications and Networking Conference Workshops , San Francisco, CA, USA, 2017.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[12]
2016 | Journal Article | IST-REx-ID: 6732 | OA
M. Mondelli, S. H. Hassani, and R. L. Urbanke, “Unified scaling of polar codes: Error exponent, scaling exponent, moderate deviations, and error floors,” IEEE Transactions on Information Theory, vol. 62, no. 12. IEEE, pp. 6698–6712, 2016.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[11]
2016 | Conference Paper | IST-REx-ID: 6733 | OA
S. Kudekar, S. Kumar, M. Mondelli, H. D. Pfister, and R. Urbankez, “Comparing the bit-MAP and block-MAP decoding thresholds of Reed-Muller codes on BMS channels,” in 2016 IEEE International Symposium on Information Theory , Barcelona, Spain, 2016, pp. 1755–1759.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[10]
2016 | Conference Paper | IST-REx-ID: 6770
M. Mondelli, S. Kudekar, S. Kumar, H. D. Pfister, E. Şaşoğlu, and R. Urbanke, “Reed-Muller codes: Thresholds and weight distribution,” in 24th International Zurich Seminar on Communications, Zurich, Switzerland, 2016, p. 50.
View | DOI
 
[9]
2015 | Journal Article | IST-REx-ID: 6737 | OA
M. Mondelli, H. Hassani, I. Sason, and R. Urbanke, “Achieving Marton’s region for broadcast channels using polar codes,” IEEE Transactions on Information Theory, vol. 61, no. 2. IEEE, pp. 783–800, 2015.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[8]
2015 | Journal Article | IST-REx-ID: 6736 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “Scaling exponent of list decoders with applications to polar codes,” IEEE Transactions on Information Theory, vol. 61, no. 9. IEEE, pp. 4838–4851, 2015.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[7]
2014 | Conference Paper | IST-REx-ID: 6740 | OA
M. Mondelli, R. Urbanke, and H. Hassani, “How to achieve the capacity of asymmetric channels,” in 52nd Annual Allerton Conference on Communication, Control, and Computing, Monticello, IL, United States, 2014, pp. 789–796.
[Preprint] View | Files available | DOI | Download Preprint (ext.) | arXiv
 
[6]
2014 | Journal Article | IST-REx-ID: 6739 | OA
M. Mondelli, H. Hassani, and R. Urbanke, “From polar to Reed-Muller codes: A technique to improve the finite-length performance,” IEEE Transactions on Communications, vol. 62, no. 9. IEEE, pp. 3084–3091, 2014.
[Preprint] View | DOI | Download Preprint (ext.) | arXiv
 
[5]
2014 | Journal Article | IST-REx-ID: 6744
M. Mondelli, Q. Zhou, V. Lottici, and X. Ma, “Joint power allocation and path selection for multi-hop noncoherent decode and forward UWB communications,” IEEE Transactions on Wireless Communications, vol. 13, no. 3. IEEE, pp. 1397–1409, 2014.
View | DOI
 
[4]
2013 | Journal Article | IST-REx-ID: 6768 | OA
M. Mondelli, “A finite difference scheme for the stack filter simulating the MCM,” Image Processing On Line, vol. 3. Image Processing On Line, pp. 68–111, 2013.
[Published Version] View | Files available | DOI
 
[3]
2012 | Conference Paper | IST-REx-ID: 6746
M. Mondelli, Q. Zhou, X. Ma, and V. Lottici, “A cooperative approach for amplify-and-forward differential transmitted reference IR-UWB relay systems,” in 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, 2012, pp. 2905–2908.
View | DOI
 
[2]
2011 | Journal Article | IST-REx-ID: 6749 | OA
M. Mondelli and A. Ciomaga, “Finite difference schemes for MCM and AMSS,” Image Processing On Line, vol. 1. IPOL Image Processing On Line, pp. 127–177, 2011.
[Published Version] View | Files available | DOI
 
[1]
2011 | Conference Paper | IST-REx-ID: 6767
M. Mondelli and A. Ciomaga, “On finite difference schemes for curvature motions,” in Proceedings of the International Student Conference on Pure and Applied Mathematics, Iasi, Romania, 2011, pp. 137–156.
View | DOI
 
Marked Publication(s)

Search

Filter Publications

    • Display / Sort

    Citation Style: IEEE

    Export / Embed