Prix Lopez-Loretta 2019 - Marco Mondelli

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.

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.

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.

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.

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.

Global convergence of deep networks with one wide layer followed by pyramidal topology
Q. Nguyen, M. Mondelli, in:, 34th Conference on Neural Information Processing Systems, Curran Associates, 2020, pp. 11961–11972.

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.

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.

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.

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.

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).

PCA initialization for approximate message passing in rotationally invariant models
M. Mondelli, R. Venkataramanan, in:, 35th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2021, pp. 29616–29629.

When are solutions connected in deep networks?
Q. Nguyen, P. Bréchet, M. Mondelli, in:, 35th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2021.

Landscape connectivity and dropout stability of SGD solutions for over-parameterized neural networks
A. Shevchenko, M. Mondelli, in:, Proceedings of the 37th International Conference on Machine Learning, ML Research Press, 2020, pp. 8773–8784.

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.

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.

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.

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.

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.

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.

Approximate message passing with spectral initialization for generalized linear models
M. Mondelli, R. Venkataramanan, Journal of Statistical Mechanics: Theory and Experiment 2022 (2022).

Approximate message passing with spectral initialization for generalized linear models
M. Mondelli, R. Venkataramanan, in:, A. Banerjee, K. Fukumizu (Eds.), Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2021, pp. 397–405.

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.

Concentration without independence via information measures
A.R. Esposito, M. Mondelli, IEEE Transactions on Information Theory (n.d.).