Marco Mondelli

You can also browse my Google Scholar profile or my CV.

Preprints

• Q. Nguyen, P. Brechet, and M. Mondelli, "On Connectivity of Solutions in Deep Learning: The Role of Over-parameterization and Feature Quality", arXiv preprint, 2021. [LINK]

• 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", arXiv preprint, 2020. [LINK]

• Q. Nguyen, M. Mondelli and G. Montufar, "Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks", arXiv preprint, 2020. [LINK]

• D. Fathollahi, N. Farsad, S. A. Hashemi, and M. Mondelli, "Sparse Multi-Decoder Recursive Projection Aggregation for Reed-Muller Codes", arXiv preprint, 2020. [LINK]

• M. Mondelli, C. Thrampoulidis, and R. Venkataramanan, "Optimal Combination of Linear and Spectral Estimators for Generalized Linear Models", arXiv preprint, 2020. [LINK]

Journal Papers

• A. Fazeli, S. H. Hassani, M. Mondelli, and A. Vardy, "Binary Linear Codes with Optimal Scaling: Polar Codes with Large Kernels", in IEEE Transactions on Information Theory, to appear. [LINK]

• M. Mondelli, S. A. Hashemi, J. Cioffi, and A. Goldsmith, "Sublinear Latency for Simplified Successive Cancellation Decoding of Polar Codes", in IEEE Transactions on Wireless Communications, to appear. [LINK]

• A. Javanmard, M. Mondelli, and A. Montanari, "Analysis of a Two-Layer Neural Network via Displacement Convexity", in Annals of Statistics, 2020. [LINK]

• S. A. Hashemi, C. Condo, M. Mondelli, and W. J. Gross, "Rate-Flexible Fast Polar Decoders", in IEEE Transactions on Signal Processing, 2019. [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "A New Coding Paradigm for the Primitive Relay Channel", in Algorithms, 2019. [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "Construction of Polar Codes with Sublinear Complexity", in IEEE Transactions on Information Theory, 2019. [LINK]

• M. Mondelli, and A. Montanari, "Fundamental Limits of Weak Recovery with Applications to Phase Retrieval", in Foundations of Computational Mathematics, 2018. [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "How to Achieve the Capacity of Asymmetric Channels", in IEEE Transactions on Information Theory, 2018. [LINK]

• S. A. Hashemi, M. Mondelli, S. H. Hassani, C. Condo, R. Urbanke, and W. J. Gross, "Decoder Partitioning: Towards Practical List Decoding of Polar Codes", in IEEE Transactions on Communications, 2018. [LINK]

• S. Kudekar, S. Kumar, M. Mondelli, H. D. Pfister, E. Şaşoğlu, and R. Urbanke, "Reed-Muller Codes Achieve Capacity on Erasure Channels", in IEEE Transactions on Information Theory, 2017. [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "Unified Scaling of Polar Codes: Error Exponent, Scaling Exponent, Moderate Deviations, and Error Floors", in IEEE Transactions on Information Theory, 2016. [LINK]

• M. Mondelli, S. H. Hassani, I. Sason, and R. Urbanke, "Scaling Exponent of List Decoders with Applications to Polar Codes", in IEEE Transactions on Information Theory, 2015. [LINK]

• M. Mondelli, S. H. Hassani, I. Sason, and R. Urbanke, "Achieving Marton's Region for Broadcast Channels Using Polar Codes", in IEEE Transactions on Information Theory, 2015. [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "From Polar to Reed-Muller Codes: a Technique to Improve the Finite-Length Performance", in IEEE Transactions on Communications, 2014. [LINK]

• M. Mondelli, Q. Zhou, V. Lottici, and X. Ma, "Joint Power Allocation and Path Selection for Multi-Hop Noncoherent Decode and Forward UWB Communications", in IEEE Transactions on Wireless Communications, 2014. [LINK]

Conference Papers

• M. Mondelli, and R. Venkataramanan, "Approximate Message Passing with Spectral Initialization for Generalized Linear Models", in Proceedings of 2021 International Conference on Artificial Intelligence and Statistics (AISTATS'21). [LINK]

• Q. Nguyen and M. Mondelli, "Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology", in Proceedings of 2020 Conference on Neural Information Processing Systems (NeurIPS'20). [LINK]

• A. Shevchenko and M. Mondelli, "Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks", in Proceedings of 2020 International Conference on Machine Learning (ICML'20). [LINK]

• M. Mondelli, S. A. Hashemi, J. Cioffi, and A. Goldsmith, "Sublinear Latency for Simplified Successive Cancellation Decoding of Polar Codes", in Proceedings of 2020 IEEE International Symposium on Information Theory (ISIT'20). [LINK]

• M. Mondelli, and A. Montanari, "On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition", in Proceedings of 2019 International Conference on Artificial Intelligence and Statistics (AISTATS'19). [LINK]

• S. A. Hashemi, C. Condo, M. Mondelli, and W. J. Gross, "Rate-Flexible Fast Polar Decoders", in Proceedings of 2019 Information Theory Workshop (ITW'19). [LINK]

• M. Mondelli, and A. Montanari, "Fundamental Limits of Weak Recovery with Applications to Phase Retrieval", extended abstract at 2018 Conference on Learning Theory (COLT'18). [LINK]

• S. A. Hashemi, N. Doan, M. Mondelli, and W. J. Gross, "Decoding Reed-Muller and Polar Codes by Successive Factor Graph Permutations", in Proceedings of 2018 International Symposium on Turbo Codes & Iterative Information Processing (ISTC'18). [LINK]

• N. Doan, S. A. Hashemi, M. Mondelli, and W. J. Gross, "On the Decoding of Polar Codes on Permuted Factor Graphs", in Proceedings of 2018 IEEE Global Communications Conference (GLOBECOM'18). [LINK]

• A. Fazeli, S. H. Hassani, M. Mondelli, and A. Vardy, "Binary Linear Codes with Optimal Scaling: Polar Codes with Large Kernels", in Proceedings of 2018 Information Theory Workshop (ITW'18). [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "A New Coding Paradigm for the Primitive Relay Channel", in Proceedings of 2018 IEEE International Symposium on Information Theory (ISIT'18). [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "Construction of Polar Codes with Sublinear Complexity", in Proceedings of 2017 IEEE International Symposium on Information Theory (ISIT'17). [LINK]

• S. A. Hashemi, M. Mondelli, S. H. Hassani, R. Urbanke, and W. J. Gross, "Partitioned List Decoding of Polar Codes: Analysis and Improvement of Finite Length Performance", in Proceedings of 2017 IEEE Global Communications Conference (GLOBECOM'17). [LINK]

• M. Mondelli, S. H. Hassani, I. Marić, D. Hui, and S.-N. Hong, "Capacity-Achieving Rate-Compatible Polar Codes for General Channels", in Proceedings of 2017 IEEE Wireless Communications and Networking Conference Workshops (WCNCW'17). [LINK]

• S. Kudekar, S. Kumar, M. Mondelli, H. D. Pfister, E. Şaşoğlu, and R. Urbanke, "Reed-Muller Codes Achieve Capacity on Erasure Channels", Best Paper Award at 2016 ACM Symposium on Theory of Computing (STOC'16). [LINK]

• S. Kudekar, S. Kumar, M. Mondelli, H. D. Pfister, and R. Urbanke, "Comparing the Bit-MAP and Block-MAP Decoding Thresholds of Reed-Muller Codes on BMS Channels", in Proceedings of 2016 IEEE International Symposium on Information Theory (ISIT'16). [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "Unified Scaling of Polar Codes: Error Exponent, Scaling Exponent, Moderate Deviations, and Error Floors", Student Paper Award at 2015 IEEE International Symposium on Information Theory (ISIT'15). [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "How to Achieve the Capacity of Asymmetric Channels", in Proceedings of 2014 Allerton Conference on Communication, Control, and Computing (ALLERTON'14). [LINK]

• M. Mondelli, S. H. Hassani, I. Sason, and R. Urbanke, "Achieving Marton's Region for Broadcast Channels Using Polar Codes", in Proceedings of 2014 IEEE International Symposium on Information Theory (ISIT'14). [LINK]

• M. Mondelli, S. H. Hassani, and R. Urbanke, "From Polar to Reed-Muller Codes: a Technique to Improve the Finite-Length Performance", in Proceedings of 2014 IEEE International Symposium on Information Theory (ISIT'14). [LINK]

• M. Mondelli, S. H. Hassani, I. Sason, and R. Urbanke, "Scaling Exponent of List Decoders with Applications to Polar Codes", in Proceedings of 2013 IEEE Information Theory Workshop (ITW'13). [LINK]

• M. Mondelli, Q. Zhou, X. Ma, and V. Lottici, "A Cooperative Approach for Amplify-and-Forward Differential Transmitted Reference IR-UWB Relay Systems", in Proceedings of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'12). [LINK]

Thesis

• M. Mondelli, "From Polar to Reed-Muller Codes: Unified Scaling, Non-standard Channels, and a Proven Conjecture", Ph.D. Thesis, EPFL, recipient of the 2018 EPFL Doctorate Award and of the 2017 Patrick Denantes Memorial Prize. [LINK]