Marco Mondelli
Mondelli Group
60 Publications
2024 | Journal Article | IST-REx-ID: 15172
Esposito AR, Mondelli M. Concentration without independence via information measures. IEEE Transactions on Information Theory. doi:10.1109/TIT.2024.3367767
View
| Files available
| DOI
| arXiv
2023 | Journal Article | IST-REx-ID: 13315 |
Barbier J, Camilli F, Mondelli M, Sáenz M. 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. 2023;120(30). doi:10.1073/pnas.2302028120
[Published Version]
View
| Files available
| DOI
| PubMed | Europe PMC
2023 | Conference Paper | IST-REx-ID: 14459 |
Shevchenko A, Kögler K, Hassani H, Mondelli M. Fundamental limits of two-layer autoencoders, and achieving them with gradient methods. In: Proceedings of the 40th International Conference on Machine Learning. Vol 202. ML Research Press; 2023:31151-31209.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 13321 |
Xu Y, Hou TQ, Liang SS, Mondelli M. Approximate message passing for multi-layer estimation in rotationally invariant models. In: 2023 IEEE Information Theory Workshop. Institute of Electrical and Electronics Engineers; 2023:294-298. doi:10.1109/ITW55543.2023.10160238
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2023 | Conference Paper | IST-REx-ID: 12859 |
Bombari S, Kiyani S, Mondelli M. 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. Vol 202. ML Research Press; 2023:2738-2776.
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14921 |
Súkeník P, Mondelli M, Lampert C. Deep neural collapse is provably optimal for the deep unconstrained features model. In: 37th Annual Conference on Neural Information Processing Systems.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14924 |
Wu D, Kungurtsev V, Mondelli M. Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence. In: Transactions on Machine Learning Research. ML Research Press; 2023.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14923 |
Fu T, Liu Y, Barbier J, Mondelli M, Liang S, Hou T. Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise. In: Proceedings of 2023 IEEE International Symposium on Information Theory. IEEE. doi:10.1109/isit54713.2023.10206671
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14922 |
Esposito AR, Mondelli M. Concentration without independence via information measures. In: Proceedings of 2023 IEEE International Symposium on Information Theory. IEEE; 2023:400-405. doi:10.1109/isit54713.2023.10206899
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Journal Article | IST-REx-ID: 11420 |
Shevchenko A, Kungurtsev V, Mondelli M. Mean-field analysis of piecewise linear solutions for wide ReLU networks. Journal of Machine Learning Research. 2022;23(130):1-55.
[Published Version]
View
| Files available
| arXiv
2022 | Conference Paper | IST-REx-ID: 12016 |
Fathollahi D, Mondelli M. Polar coded computing: The role of the scaling exponent. In: 2022 IEEE International Symposium on Information Theory. Vol 2022. IEEE; 2022:2154-2159. doi:10.1109/ISIT50566.2022.9834712
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Conference Paper | IST-REx-ID: 12540 |
Venkataramanan R, Kögler K, Mondelli M. Estimation in rotationally invariant generalized linear models via approximate message passing. In: Proceedings of the 39th International Conference on Machine Learning. Vol 162. ML Research Press; 2022.
[Published Version]
View
| Files available
2022 | Preprint | IST-REx-ID: 12536 |
Barbier J, Hou T, Mondelli M, Saenz M. The price of ignorance: How much does it cost to forget noise structure in low-rank matrix estimation? arXiv. doi:10.48550/arXiv.2205.10009
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Journal Article | IST-REx-ID: 12233 |
Doan N, Hashemi SA, Mondelli M, Gross WJ. Decoding Reed-Muller codes with successive codeword permutations. IEEE Transactions on Communications. 2022;70(11):7134-7145. doi:10.1109/tcomm.2022.3211101
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2022 | Journal Article | IST-REx-ID: 10364 |
Hashemi SA, Mondelli M, Fazeli A, Vardy A, Cioffi J, Goldsmith A. Parallelism versus latency in simplified successive-cancellation decoding of polar codes. IEEE Transactions on Wireless Communications. 2022;21(6):3909-3920. doi:10.1109/TWC.2021.3125626
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2022 | Journal Article | IST-REx-ID: 12538 |
Amani MH, Bombari S, Mondelli M, Pukdee R, Rini S. Sharp asymptotics on the compression of two-layer neural networks. IEEE Information Theory Workshop. 2022:588-593. doi:10.1109/ITW54588.2022.9965870
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Conference Paper | IST-REx-ID: 12537 |
Bombari S, Amani MH, Mondelli M. Memorization and optimization in deep neural networks with minimum over-parameterization. In: 36th Conference on Neural Information Processing Systems. Vol 35. Curran Associates; 2022:7628-7640.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Journal Article | IST-REx-ID: 12480 |
Mondelli M, Venkataramanan R. Approximate message passing with spectral initialization for generalized linear models. Journal of Statistical Mechanics: Theory and Experiment. 2022;2022(11). doi:10.1088/1742-5468/ac9828
[Published Version]
View
| Files available
| DOI
| WoS
2021 | Conference Paper | IST-REx-ID: 10595 |
Nguyen Q, Mondelli M, Montufar GF. Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep ReLU networks. In: Meila M, Zhang T, eds. Proceedings of the 38th International Conference on Machine Learning. Vol 139. ML Research Press; 2021:8119-8129.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 10599 |
Hashemi SA, Mondelli M, Cioffi J, Goldsmith A. Successive syndrome-check decoding of polar codes. In: Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers. Vol 2021-October. Institute of Electrical and Electronics Engineers; 2021:943-947. doi:10.1109/IEEECONF53345.2021.9723394
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 13146 |
Nguyen Q, Mondelli M, Montufar G. 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. Vol 139. ML Research Press; 2021:8119-8129.
[Published Version]
View
| Files available
| arXiv
2021 | Journal Article | IST-REx-ID: 9047 |
Mondelli M, Hashemi SA, Cioffi JM, Goldsmith A. Sublinear latency for simplified successive cancellation decoding of polar codes. IEEE Transactions on Wireless Communications. 2021;20(1):18-27. doi:10.1109/TWC.2020.3022922
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2021 | Conference Paper | IST-REx-ID: 10053 |
Hashemi SA, Mondelli M, Fazeli A, Vardy A, Cioffi J, Goldsmith A. Parallelism versus latency in simplified successive-cancellation decoding of polar codes. In: 2021 IEEE International Symposium on Information Theory. Institute of Electrical and Electronics Engineers; 2021:2369-2374. doi:10.1109/ISIT45174.2021.9518153
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2021 | Conference Paper | IST-REx-ID: 10597 |
Fathollahi D, Farsad N, Hashemi SA, Mondelli M. Sparse multi-decoder recursive projection aggregation for Reed-Muller codes. In: 2021 IEEE International Symposium on Information Theory. Institute of Electrical and Electronics Engineers; 2021:1082-1087. doi:10.1109/isit45174.2021.9517887
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2021 | Journal Article | IST-REx-ID: 10211 |
Mondelli M, Thrampoulidis C, Venkataramanan R. Optimal combination of linear and spectral estimators for generalized linear models. Foundations of Computational Mathematics. 2021. doi:10.1007/s10208-021-09531-x
[Published Version]
View
| Files available
| DOI
| WoS
| arXiv
2021 | Conference Paper | IST-REx-ID: 10593 |
Mondelli M, Venkataramanan R. PCA initialization for approximate message passing in rotationally invariant models. In: 35th Conference on Neural Information Processing Systems. Vol 35. Neural Information Processing Systems Foundation; 2021:29616-29629.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 10594 |
Nguyen Q, Bréchet P, Mondelli M. When are solutions connected in deep networks? In: 35th Conference on Neural Information Processing Systems. Vol 35. Neural Information Processing Systems Foundation; 2021.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 10598 |
Mondelli M, Venkataramanan R. Approximate message passing with spectral initialization for generalized linear models. In: Banerjee A, Fukumizu K, eds. Proceedings of The 24th International Conference on Artificial Intelligence and Statistics. Vol 130. ML Research Press; 2021:397-405.
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
2021 | Journal Article | IST-REx-ID: 9002
Fazeli A, Hassani H, Mondelli M, Vardy A. Binary linear codes with optimal scaling: Polar codes with large kernels. IEEE Transactions on Information Theory. 2021;67(9):5693-5710. doi:10.1109/TIT.2020.3038806
[Preprint]
View
| Files available
| DOI
| arXiv
2020 | Conference Paper | IST-REx-ID: 9221 |
Nguyen Q, Mondelli M. Global convergence of deep networks with one wide layer followed by pyramidal topology. In: 34th Conference on Neural Information Processing Systems. Vol 33. Curran Associates; 2020:11961–11972.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2020 | Conference Paper | IST-REx-ID: 8536 |
Mondelli M, Hashemi SA, Cioffi J, Goldsmith A. Simplified successive cancellation decoding of polar codes has sublinear latency. In: IEEE International Symposium on Information Theory - Proceedings. Vol 2020-June. IEEE; 2020. doi:10.1109/ISIT44484.2020.9174141
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2020 | Conference Paper | IST-REx-ID: 9198 |
Shevchenko A, Mondelli M. Landscape connectivity and dropout stability of SGD solutions for over-parameterized neural networks. In: Proceedings of the 37th International Conference on Machine Learning. Vol 119. ML Research Press; 2020:8773-8784.
[Published Version]
View
| Files available
| arXiv
2020 | Journal Article | IST-REx-ID: 6748 |
Javanmard A, Mondelli M, Montanari A. Analysis of a two-layer neural network via displacement convexity. Annals of Statistics. 2020;48(6):3619-3642. doi:10.1214/20-AOS1945
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2019 | Journal Article | IST-REx-ID: 6662 |
Mondelli M, Montanari A. Fundamental limits of weak recovery with applications to phase retrieval. Foundations of Computational Mathematics. 2019;19(3):703-773. doi:10.1007/s10208-018-9395-y
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2019 | Journal Article | IST-REx-ID: 6663 |
Mondelli M, Hassani H, Urbanke R. Construction of polar codes with sublinear complexity. IEEE. 2019;65(5):2782-2791. doi:10.1109/tit.2018.2889667
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2019 | Conference Paper | IST-REx-ID: 6747 |
Mondelli M, Montanari A. On the connection between learning two-layers neural networks and tensor decomposition. In: Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics. Vol 89. Proceedings of Machine Learning Research; 2019:1051-1060.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2019 | Journal Article | IST-REx-ID: 6750 |
Hashemi SA, Condo C, Mondelli M, Gross WJ. Rate-flexible fast polar decoders. IEEE Transactions on Signal Processing. 2019;67(22). doi:10.1109/TSP.2019.2944738
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2019 | Journal Article | IST-REx-ID: 7007 |
Mondelli M, Hassani SH, Urbanke R. A new coding paradigm for the primitive relay channel. Algorithms. 2019;12(10). doi:10.3390/a12100218
[Published Version]
View
| Files available
| DOI
| arXiv
2018 | Conference Paper | IST-REx-ID: 6664 |
Hashemi SA, Doan N, Mondelli M, Gross W. Decoding Reed-Muller and polar codes by successive factor graph permutations. In: 2018 IEEE 10th International Symposium on Turbo Codes & Iterative Information Processing. IEEE; 2018:1-5. doi:10.1109/istc.2018.8625281
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2018 | Journal Article | IST-REx-ID: 6674
Hashemi SA, Mondelli M, Hassani SH, Condo C, Urbanke RL, Gross WJ. Decoder partitioning: Towards practical list decoding of polar codes. IEEE Transactions on Communications. 2018;66(9):3749-3759. doi:10.1109/tcomm.2018.2832207
View
| DOI
2018 | Conference Paper | IST-REx-ID: 6728 |
Doan N, Hashemi SA, Mondelli M, Gross WJ. On the decoding of polar codes on permuted factor graphs. In: 2018 IEEE Global Communications Conference . IEEE; 2018. doi:10.1109/glocom.2018.8647308
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2018 | Journal Article | IST-REx-ID: 6678 |
Mondelli M, Hassani H, Urbanke R. How to achieve the capacity of asymmetric channels. IEEE Transactions on Information Theory. 2018;64(5):3371-3393. doi:10.1109/tit.2018.2789885
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2018 | Conference Paper | IST-REx-ID: 6675 |
Mondelli M, Hassani H, Urbanke R. A new coding paradigm for the primitive relay channel. In: 2018 IEEE International Symposium on Information Theory. IEEE; 2018:351-355. doi:10.1109/isit.2018.8437479
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2018 | Conference Paper | IST-REx-ID: 6665 |
Fazeli A, Hassani H, Mondelli M, Vardy A. Binary linear codes with optimal scaling: Polar codes with large kernels. In: 2018 IEEE Information Theory Workshop. IEEE; 2018:1-5. doi:10.1109/itw.2018.8613428
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2017 | Conference Paper | IST-REx-ID: 6679 |
Hashemi SA, Mondelli M, Hassani H, Urbanke R, Gross W. Partitioned list decoding of polar codes: Analysis and improvement of finite length performance. In: 2017 IEEE Global Communications Conference. IEEE; 2017:1-7. doi:10.1109/glocom.2017.8254940
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2017 | Conference Paper | IST-REx-ID: 6729 |
Mondelli M, Hassani SH, Urbanke R. Construction of polar codes with sublinear complexity. In: 2017 IEEE International Symposium on Information Theory . IEEE; 2017:1853-1857. doi:10.1109/isit.2017.8006850
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2017 | Journal Article | IST-REx-ID: 6730 |
Kudekar S, Kumar S, Mondelli M, Pfister HD, Sasoglu E, Urbanke RL. Reed–Muller codes achieve capacity on erasure channels. IEEE Transactions on Information Theory. 2017;63(7):4298-4316. doi:10.1109/tit.2017.2673829
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2017 | Conference Paper | IST-REx-ID: 6731 |
Mondelli M, Hassani H, Maric I, Hui D, Hong S-N. Capacity-achieving rate-compatible polar codes for general channels. In: 2017 IEEE Wireless Communications and Networking Conference Workshops . IEEE; 2017. doi:10.1109/wcncw.2017.7919107
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2016 | Journal Article | IST-REx-ID: 6732 |
Mondelli M, Hassani SH, Urbanke RL. Unified scaling of polar codes: Error exponent, scaling exponent, moderate deviations, and error floors. IEEE Transactions on Information Theory. 2016;62(12):6698-6712. doi:10.1109/tit.2016.2616117
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2016 | Conference Paper | IST-REx-ID: 6733 |
Kudekar S, Kumar S, Mondelli M, Pfister HD, Urbankez R. Comparing the bit-MAP and block-MAP decoding thresholds of Reed-Muller codes on BMS channels. In: 2016 IEEE International Symposium on Information Theory . IEEE; 2016:1755-1759. doi:10.1109/isit.2016.7541600
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2016 | Conference Paper | IST-REx-ID: 6770
Mondelli M, Kudekar S, Kumar S, Pfister HD, Şaşoğlu E, Urbanke R. Reed-Muller codes: Thresholds and weight distribution. In: 24th International Zurich Seminar on Communications. ETH Zürich; 2016:50. doi:10.3929/ETHZ-A-010646484
View
| DOI
2015 | Journal Article | IST-REx-ID: 6737 |
Mondelli M, Hassani H, Sason I, Urbanke R. Achieving Marton’s region for broadcast channels using polar codes. IEEE Transactions on Information Theory. 2015;61(2):783-800. doi:10.1109/tit.2014.2368555
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2015 | Journal Article | IST-REx-ID: 6736 |
Mondelli M, Hassani H, Urbanke R. Scaling exponent of list decoders with applications to polar codes. IEEE Transactions on Information Theory. 2015;61(9):4838-4851. doi:10.1109/tit.2015.2453315
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2014 | Conference Paper | IST-REx-ID: 6740 |
Mondelli M, Urbanke R, Hassani H. How to achieve the capacity of asymmetric channels. In: 52nd Annual Allerton Conference on Communication, Control, and Computing. IEEE; 2014:789-796. doi:10.1109/allerton.2014.7028535
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2014 | Journal Article | IST-REx-ID: 6739 |
Mondelli M, Hassani H, Urbanke R. From polar to Reed-Muller codes: A technique to improve the finite-length performance. IEEE Transactions on Communications. 2014;62(9):3084-3091. doi:10.1109/tcomm.2014.2345069
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2014 | Journal Article | IST-REx-ID: 6744
Mondelli M, Zhou Q, Lottici V, Ma X. Joint power allocation and path selection for multi-hop noncoherent decode and forward UWB communications. IEEE Transactions on Wireless Communications. 2014;13(3):1397-1409. doi:10.1109/twc.2014.020914.130669
View
| DOI
2013 | Journal Article | IST-REx-ID: 6768 |
Mondelli M. A finite difference scheme for the stack filter simulating the MCM. Image Processing On Line. 2013;3:68-111. doi:10.5201/ipol.2013.53
[Published Version]
View
| Files available
| DOI
2012 | Conference Paper | IST-REx-ID: 6746
Mondelli M, Zhou Q, Ma X, Lottici V. 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). IEEE; 2012:2905-2908. doi:10.1109/icassp.2012.6288524
View
| DOI
2011 | Journal Article | IST-REx-ID: 6749 |
Mondelli M, Ciomaga A. Finite difference schemes for MCM and AMSS. Image Processing On Line. 2011;1:127-177. doi:10.5201/ipol.2011.cm_fds
[Published Version]
View
| Files available
| DOI
2011 | Conference Paper | IST-REx-ID: 6767
Mondelli M, Ciomaga A. On finite difference schemes for curvature motions. In: Proceedings of the International Student Conference on Pure and Applied Mathematics. Editura Universitãtii „Alexandru Ioan Cuza” Iasi; 2011:137-156. doi:10.13140/2.1.1862.4646
View
| DOI
60 Publications
2024 | Journal Article | IST-REx-ID: 15172
Esposito AR, Mondelli M. Concentration without independence via information measures. IEEE Transactions on Information Theory. doi:10.1109/TIT.2024.3367767
View
| Files available
| DOI
| arXiv
2023 | Journal Article | IST-REx-ID: 13315 |
Barbier J, Camilli F, Mondelli M, Sáenz M. 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. 2023;120(30). doi:10.1073/pnas.2302028120
[Published Version]
View
| Files available
| DOI
| PubMed | Europe PMC
2023 | Conference Paper | IST-REx-ID: 14459 |
Shevchenko A, Kögler K, Hassani H, Mondelli M. Fundamental limits of two-layer autoencoders, and achieving them with gradient methods. In: Proceedings of the 40th International Conference on Machine Learning. Vol 202. ML Research Press; 2023:31151-31209.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 13321 |
Xu Y, Hou TQ, Liang SS, Mondelli M. Approximate message passing for multi-layer estimation in rotationally invariant models. In: 2023 IEEE Information Theory Workshop. Institute of Electrical and Electronics Engineers; 2023:294-298. doi:10.1109/ITW55543.2023.10160238
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2023 | Conference Paper | IST-REx-ID: 12859 |
Bombari S, Kiyani S, Mondelli M. 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. Vol 202. ML Research Press; 2023:2738-2776.
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14921 |
Súkeník P, Mondelli M, Lampert C. Deep neural collapse is provably optimal for the deep unconstrained features model. In: 37th Annual Conference on Neural Information Processing Systems.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14924 |
Wu D, Kungurtsev V, Mondelli M. Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence. In: Transactions on Machine Learning Research. ML Research Press; 2023.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14923 |
Fu T, Liu Y, Barbier J, Mondelli M, Liang S, Hou T. Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise. In: Proceedings of 2023 IEEE International Symposium on Information Theory. IEEE. doi:10.1109/isit54713.2023.10206671
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2023 | Conference Paper | IST-REx-ID: 14922 |
Esposito AR, Mondelli M. Concentration without independence via information measures. In: Proceedings of 2023 IEEE International Symposium on Information Theory. IEEE; 2023:400-405. doi:10.1109/isit54713.2023.10206899
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Journal Article | IST-REx-ID: 11420 |
Shevchenko A, Kungurtsev V, Mondelli M. Mean-field analysis of piecewise linear solutions for wide ReLU networks. Journal of Machine Learning Research. 2022;23(130):1-55.
[Published Version]
View
| Files available
| arXiv
2022 | Conference Paper | IST-REx-ID: 12016 |
Fathollahi D, Mondelli M. Polar coded computing: The role of the scaling exponent. In: 2022 IEEE International Symposium on Information Theory. Vol 2022. IEEE; 2022:2154-2159. doi:10.1109/ISIT50566.2022.9834712
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Conference Paper | IST-REx-ID: 12540 |
Venkataramanan R, Kögler K, Mondelli M. Estimation in rotationally invariant generalized linear models via approximate message passing. In: Proceedings of the 39th International Conference on Machine Learning. Vol 162. ML Research Press; 2022.
[Published Version]
View
| Files available
2022 | Preprint | IST-REx-ID: 12536 |
Barbier J, Hou T, Mondelli M, Saenz M. The price of ignorance: How much does it cost to forget noise structure in low-rank matrix estimation? arXiv. doi:10.48550/arXiv.2205.10009
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Journal Article | IST-REx-ID: 12233 |
Doan N, Hashemi SA, Mondelli M, Gross WJ. Decoding Reed-Muller codes with successive codeword permutations. IEEE Transactions on Communications. 2022;70(11):7134-7145. doi:10.1109/tcomm.2022.3211101
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2022 | Journal Article | IST-REx-ID: 10364 |
Hashemi SA, Mondelli M, Fazeli A, Vardy A, Cioffi J, Goldsmith A. Parallelism versus latency in simplified successive-cancellation decoding of polar codes. IEEE Transactions on Wireless Communications. 2022;21(6):3909-3920. doi:10.1109/TWC.2021.3125626
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2022 | Journal Article | IST-REx-ID: 12538 |
Amani MH, Bombari S, Mondelli M, Pukdee R, Rini S. Sharp asymptotics on the compression of two-layer neural networks. IEEE Information Theory Workshop. 2022:588-593. doi:10.1109/ITW54588.2022.9965870
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2022 | Conference Paper | IST-REx-ID: 12537 |
Bombari S, Amani MH, Mondelli M. Memorization and optimization in deep neural networks with minimum over-parameterization. In: 36th Conference on Neural Information Processing Systems. Vol 35. Curran Associates; 2022:7628-7640.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2022 | Journal Article | IST-REx-ID: 12480 |
Mondelli M, Venkataramanan R. Approximate message passing with spectral initialization for generalized linear models. Journal of Statistical Mechanics: Theory and Experiment. 2022;2022(11). doi:10.1088/1742-5468/ac9828
[Published Version]
View
| Files available
| DOI
| WoS
2021 | Conference Paper | IST-REx-ID: 10595 |
Nguyen Q, Mondelli M, Montufar GF. Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep ReLU networks. In: Meila M, Zhang T, eds. Proceedings of the 38th International Conference on Machine Learning. Vol 139. ML Research Press; 2021:8119-8129.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 10599 |
Hashemi SA, Mondelli M, Cioffi J, Goldsmith A. Successive syndrome-check decoding of polar codes. In: Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers. Vol 2021-October. Institute of Electrical and Electronics Engineers; 2021:943-947. doi:10.1109/IEEECONF53345.2021.9723394
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 13146 |
Nguyen Q, Mondelli M, Montufar G. 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. Vol 139. ML Research Press; 2021:8119-8129.
[Published Version]
View
| Files available
| arXiv
2021 | Journal Article | IST-REx-ID: 9047 |
Mondelli M, Hashemi SA, Cioffi JM, Goldsmith A. Sublinear latency for simplified successive cancellation decoding of polar codes. IEEE Transactions on Wireless Communications. 2021;20(1):18-27. doi:10.1109/TWC.2020.3022922
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2021 | Conference Paper | IST-REx-ID: 10053 |
Hashemi SA, Mondelli M, Fazeli A, Vardy A, Cioffi J, Goldsmith A. Parallelism versus latency in simplified successive-cancellation decoding of polar codes. In: 2021 IEEE International Symposium on Information Theory. Institute of Electrical and Electronics Engineers; 2021:2369-2374. doi:10.1109/ISIT45174.2021.9518153
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2021 | Conference Paper | IST-REx-ID: 10597 |
Fathollahi D, Farsad N, Hashemi SA, Mondelli M. Sparse multi-decoder recursive projection aggregation for Reed-Muller codes. In: 2021 IEEE International Symposium on Information Theory. Institute of Electrical and Electronics Engineers; 2021:1082-1087. doi:10.1109/isit45174.2021.9517887
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2021 | Journal Article | IST-REx-ID: 10211 |
Mondelli M, Thrampoulidis C, Venkataramanan R. Optimal combination of linear and spectral estimators for generalized linear models. Foundations of Computational Mathematics. 2021. doi:10.1007/s10208-021-09531-x
[Published Version]
View
| Files available
| DOI
| WoS
| arXiv
2021 | Conference Paper | IST-REx-ID: 10593 |
Mondelli M, Venkataramanan R. PCA initialization for approximate message passing in rotationally invariant models. In: 35th Conference on Neural Information Processing Systems. Vol 35. Neural Information Processing Systems Foundation; 2021:29616-29629.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 10594 |
Nguyen Q, Bréchet P, Mondelli M. When are solutions connected in deep networks? In: 35th Conference on Neural Information Processing Systems. Vol 35. Neural Information Processing Systems Foundation; 2021.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2021 | Conference Paper | IST-REx-ID: 10598 |
Mondelli M, Venkataramanan R. Approximate message passing with spectral initialization for generalized linear models. In: Banerjee A, Fukumizu K, eds. Proceedings of The 24th International Conference on Artificial Intelligence and Statistics. Vol 130. ML Research Press; 2021:397-405.
[Preprint]
View
| Files available
| Download Preprint (ext.)
| arXiv
2021 | Journal Article | IST-REx-ID: 9002
Fazeli A, Hassani H, Mondelli M, Vardy A. Binary linear codes with optimal scaling: Polar codes with large kernels. IEEE Transactions on Information Theory. 2021;67(9):5693-5710. doi:10.1109/TIT.2020.3038806
[Preprint]
View
| Files available
| DOI
| arXiv
2020 | Conference Paper | IST-REx-ID: 9221 |
Nguyen Q, Mondelli M. Global convergence of deep networks with one wide layer followed by pyramidal topology. In: 34th Conference on Neural Information Processing Systems. Vol 33. Curran Associates; 2020:11961–11972.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2020 | Conference Paper | IST-REx-ID: 8536 |
Mondelli M, Hashemi SA, Cioffi J, Goldsmith A. Simplified successive cancellation decoding of polar codes has sublinear latency. In: IEEE International Symposium on Information Theory - Proceedings. Vol 2020-June. IEEE; 2020. doi:10.1109/ISIT44484.2020.9174141
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2020 | Conference Paper | IST-REx-ID: 9198 |
Shevchenko A, Mondelli M. Landscape connectivity and dropout stability of SGD solutions for over-parameterized neural networks. In: Proceedings of the 37th International Conference on Machine Learning. Vol 119. ML Research Press; 2020:8773-8784.
[Published Version]
View
| Files available
| arXiv
2020 | Journal Article | IST-REx-ID: 6748 |
Javanmard A, Mondelli M, Montanari A. Analysis of a two-layer neural network via displacement convexity. Annals of Statistics. 2020;48(6):3619-3642. doi:10.1214/20-AOS1945
[Preprint]
View
| DOI
| Download Preprint (ext.)
| WoS
| arXiv
2019 | Journal Article | IST-REx-ID: 6662 |
Mondelli M, Montanari A. Fundamental limits of weak recovery with applications to phase retrieval. Foundations of Computational Mathematics. 2019;19(3):703-773. doi:10.1007/s10208-018-9395-y
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2019 | Journal Article | IST-REx-ID: 6663 |
Mondelli M, Hassani H, Urbanke R. Construction of polar codes with sublinear complexity. IEEE. 2019;65(5):2782-2791. doi:10.1109/tit.2018.2889667
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2019 | Conference Paper | IST-REx-ID: 6747 |
Mondelli M, Montanari A. On the connection between learning two-layers neural networks and tensor decomposition. In: Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics. Vol 89. Proceedings of Machine Learning Research; 2019:1051-1060.
[Preprint]
View
| Download Preprint (ext.)
| arXiv
2019 | Journal Article | IST-REx-ID: 6750 |
Hashemi SA, Condo C, Mondelli M, Gross WJ. Rate-flexible fast polar decoders. IEEE Transactions on Signal Processing. 2019;67(22). doi:10.1109/TSP.2019.2944738
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2019 | Journal Article | IST-REx-ID: 7007 |
Mondelli M, Hassani SH, Urbanke R. A new coding paradigm for the primitive relay channel. Algorithms. 2019;12(10). doi:10.3390/a12100218
[Published Version]
View
| Files available
| DOI
| arXiv
2018 | Conference Paper | IST-REx-ID: 6664 |
Hashemi SA, Doan N, Mondelli M, Gross W. Decoding Reed-Muller and polar codes by successive factor graph permutations. In: 2018 IEEE 10th International Symposium on Turbo Codes & Iterative Information Processing. IEEE; 2018:1-5. doi:10.1109/istc.2018.8625281
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2018 | Journal Article | IST-REx-ID: 6674
Hashemi SA, Mondelli M, Hassani SH, Condo C, Urbanke RL, Gross WJ. Decoder partitioning: Towards practical list decoding of polar codes. IEEE Transactions on Communications. 2018;66(9):3749-3759. doi:10.1109/tcomm.2018.2832207
View
| DOI
2018 | Conference Paper | IST-REx-ID: 6728 |
Doan N, Hashemi SA, Mondelli M, Gross WJ. On the decoding of polar codes on permuted factor graphs. In: 2018 IEEE Global Communications Conference . IEEE; 2018. doi:10.1109/glocom.2018.8647308
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2018 | Journal Article | IST-REx-ID: 6678 |
Mondelli M, Hassani H, Urbanke R. How to achieve the capacity of asymmetric channels. IEEE Transactions on Information Theory. 2018;64(5):3371-3393. doi:10.1109/tit.2018.2789885
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2018 | Conference Paper | IST-REx-ID: 6675 |
Mondelli M, Hassani H, Urbanke R. A new coding paradigm for the primitive relay channel. In: 2018 IEEE International Symposium on Information Theory. IEEE; 2018:351-355. doi:10.1109/isit.2018.8437479
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2018 | Conference Paper | IST-REx-ID: 6665 |
Fazeli A, Hassani H, Mondelli M, Vardy A. Binary linear codes with optimal scaling: Polar codes with large kernels. In: 2018 IEEE Information Theory Workshop. IEEE; 2018:1-5. doi:10.1109/itw.2018.8613428
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2017 | Conference Paper | IST-REx-ID: 6679 |
Hashemi SA, Mondelli M, Hassani H, Urbanke R, Gross W. Partitioned list decoding of polar codes: Analysis and improvement of finite length performance. In: 2017 IEEE Global Communications Conference. IEEE; 2017:1-7. doi:10.1109/glocom.2017.8254940
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2017 | Conference Paper | IST-REx-ID: 6729 |
Mondelli M, Hassani SH, Urbanke R. Construction of polar codes with sublinear complexity. In: 2017 IEEE International Symposium on Information Theory . IEEE; 2017:1853-1857. doi:10.1109/isit.2017.8006850
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2017 | Journal Article | IST-REx-ID: 6730 |
Kudekar S, Kumar S, Mondelli M, Pfister HD, Sasoglu E, Urbanke RL. Reed–Muller codes achieve capacity on erasure channels. IEEE Transactions on Information Theory. 2017;63(7):4298-4316. doi:10.1109/tit.2017.2673829
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2017 | Conference Paper | IST-REx-ID: 6731 |
Mondelli M, Hassani H, Maric I, Hui D, Hong S-N. Capacity-achieving rate-compatible polar codes for general channels. In: 2017 IEEE Wireless Communications and Networking Conference Workshops . IEEE; 2017. doi:10.1109/wcncw.2017.7919107
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2016 | Journal Article | IST-REx-ID: 6732 |
Mondelli M, Hassani SH, Urbanke RL. Unified scaling of polar codes: Error exponent, scaling exponent, moderate deviations, and error floors. IEEE Transactions on Information Theory. 2016;62(12):6698-6712. doi:10.1109/tit.2016.2616117
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2016 | Conference Paper | IST-REx-ID: 6733 |
Kudekar S, Kumar S, Mondelli M, Pfister HD, Urbankez R. Comparing the bit-MAP and block-MAP decoding thresholds of Reed-Muller codes on BMS channels. In: 2016 IEEE International Symposium on Information Theory . IEEE; 2016:1755-1759. doi:10.1109/isit.2016.7541600
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2016 | Conference Paper | IST-REx-ID: 6770
Mondelli M, Kudekar S, Kumar S, Pfister HD, Şaşoğlu E, Urbanke R. Reed-Muller codes: Thresholds and weight distribution. In: 24th International Zurich Seminar on Communications. ETH Zürich; 2016:50. doi:10.3929/ETHZ-A-010646484
View
| DOI
2015 | Journal Article | IST-REx-ID: 6737 |
Mondelli M, Hassani H, Sason I, Urbanke R. Achieving Marton’s region for broadcast channels using polar codes. IEEE Transactions on Information Theory. 2015;61(2):783-800. doi:10.1109/tit.2014.2368555
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2015 | Journal Article | IST-REx-ID: 6736 |
Mondelli M, Hassani H, Urbanke R. Scaling exponent of list decoders with applications to polar codes. IEEE Transactions on Information Theory. 2015;61(9):4838-4851. doi:10.1109/tit.2015.2453315
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2014 | Conference Paper | IST-REx-ID: 6740 |
Mondelli M, Urbanke R, Hassani H. How to achieve the capacity of asymmetric channels. In: 52nd Annual Allerton Conference on Communication, Control, and Computing. IEEE; 2014:789-796. doi:10.1109/allerton.2014.7028535
[Preprint]
View
| Files available
| DOI
| Download Preprint (ext.)
| arXiv
2014 | Journal Article | IST-REx-ID: 6739 |
Mondelli M, Hassani H, Urbanke R. From polar to Reed-Muller codes: A technique to improve the finite-length performance. IEEE Transactions on Communications. 2014;62(9):3084-3091. doi:10.1109/tcomm.2014.2345069
[Preprint]
View
| DOI
| Download Preprint (ext.)
| arXiv
2014 | Journal Article | IST-REx-ID: 6744
Mondelli M, Zhou Q, Lottici V, Ma X. Joint power allocation and path selection for multi-hop noncoherent decode and forward UWB communications. IEEE Transactions on Wireless Communications. 2014;13(3):1397-1409. doi:10.1109/twc.2014.020914.130669
View
| DOI
2013 | Journal Article | IST-REx-ID: 6768 |
Mondelli M. A finite difference scheme for the stack filter simulating the MCM. Image Processing On Line. 2013;3:68-111. doi:10.5201/ipol.2013.53
[Published Version]
View
| Files available
| DOI
2012 | Conference Paper | IST-REx-ID: 6746
Mondelli M, Zhou Q, Ma X, Lottici V. 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). IEEE; 2012:2905-2908. doi:10.1109/icassp.2012.6288524
View
| DOI
2011 | Journal Article | IST-REx-ID: 6749 |
Mondelli M, Ciomaga A. Finite difference schemes for MCM and AMSS. Image Processing On Line. 2011;1:127-177. doi:10.5201/ipol.2011.cm_fds
[Published Version]
View
| Files available
| DOI
2011 | Conference Paper | IST-REx-ID: 6767
Mondelli M, Ciomaga A. On finite difference schemes for curvature motions. In: Proceedings of the International Student Conference on Pure and Applied Mathematics. Editura Universitãtii „Alexandru Ioan Cuza” Iasi; 2011:137-156. doi:10.13140/2.1.1862.4646
View
| DOI