| 2025 | COLT | Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery. | Filip Kovacevic, Yihan Zhang, Marco Mondelli |
| 2025 | ICLR | High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws. | Muhammed Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga, Marco Mondelli, Samet Oymak |
| 2025 | ICLR | Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse. | Arthur Jacot, Peter Skenk, Zihan Wang, Marco Mondelli |
| 2025 | ICML | Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization. | Simone Bombari, Marco Mondelli |
| 2025 | ICML | Test-Time Training Provably Improves Transformers as In-context Learners. | Halil Alperen Gozeten, Muhammed Emrullah Ildiz, Xuechen Zhang, Mahdi Soltanolkotabi, Marco Mondelli, Samet Oymak |
| 2025 | ICML | Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime. | Diyuan Wu, Marco Mondelli |
| 2024 | COLT | Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing (Extended Abstract). | Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan, Marco Mondelli |
| 2024 | COLT | Contraction of Markovian Operators in Orlicz Spaces and Error Bounds for Markov Chain Monte Carlo (Extended Abstract). | Amedeo Roberto Esposito, Marco Mondelli |
| 2024 | ICASSP | Inference of Genetic Effects via Approximate Message Passing. | Al Depope, Marco Mondelli, Matthew R. Robinson |
| 2024 | ICML | How Spurious Features are Memorized: Precise Analysis for Random and NTK Features. | Simone Bombari, Marco Mondelli |
| 2024 | ICML | Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features. | Simone Bombari, Marco Mondelli |
| 2024 | ICML | Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth. | Kevin Kgler, Aleksandr Shevchenko, Hamed Hassani, Marco Mondelli |
| 2023 | ICML | Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels. | Simone Bombari, Shayan Kiyani, Marco Mondelli |
| 2023 | ICML | Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods. | Aleksandr Shevchenko, Kevin Kgler, Hamed Hassani, Marco Mondelli |
| 2023 | ISIT | Concentration without Independence via Information Measures. | Amedeo Roberto Esposito, Marco Mondelli |
| 2023 | ISIT | Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise. | Teng Fu, Yuhao Liu, Jean Barbier, Marco Mondelli, Shansuo Liang, TianQi Hou |
| 2023 | ITW | Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Models. | Yizhou Xu, TianQi Hou, Shansuo Liang, Marco Mondelli |
| 2022 | ICML | Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing. | Ramji Venkataramanan, Kevin Kgler, Marco Mondelli |
| 2022 | ISIT | Polar Coded Computing: The Role of the Scaling Exponent. | Dorsa Fathollahi, Marco Mondelli |
| 2022 | ITW | Sharp asymptotics on the compression of two-layer neural networks. | Mohammad Hossein Amani, Simone Bombari, Marco Mondelli, Rattana Pukdee, Stefano Rini |
| 2021 | ACSSC | Successive Syndrome-Check Decoding of Polar Codes. | Seyyed Ali Hashemi, Marco Mondelli, John M. Cioffi, Andrea Goldsmith |
| 2021 | AISTATS | Approximate Message Passing with Spectral Initialization for Generalized Linear Models. | Marco Mondelli, Ramji Venkataramanan |
| 2021 | ICML | Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks. | Quynh Nguyen, Marco Mondelli, Guido F. Montfar |
| 2021 | ISIT | Sparse Multi-Decoder Recursive Projection Aggregation for Reed-Muller Codes. | Dorsa Fathollahi, Nariman Farsad, Seyyed Ali Hashemi, Marco Mondelli |
| 2021 | ISIT | Parallelism versus Latency in Simplified Successive-Cancellation Decoding of Polar Codes. | Seyyed Ali Hashemi, Marco Mondelli, Arman Fazeli, Alexander Vardy, John M. Cioffi, Andrea Goldsmith |
| 2020 | ICML | Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks. | Alexander Shevchenko, Marco Mondelli |
| 2020 | ISIT | Simplified Successive Cancellation Decoding of Polar Codes Has Sublinear Latency. | Marco Mondelli, Seyyed Ali Hashemi, John M. Cioffi, Andrea Goldsmith |
| 2019 | AISTATS | On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition. | Marco Mondelli, Andrea Montanari |
| 2019 | ITW | Rate-Flexible Fast Polar Decoders. | Seyyed Ali Hashemi, Carlo Condo, Marco Mondelli, Warren J. Gross |
| 2018 | COLT | Fundamental Limits of Weak Recovery with Applications to Phase Retrieval. | Marco Mondelli, Andrea Montanari |
| 2018 | GLOBECOM | On the Decoding of Polar Codes on Permuted Factor Graphs. | Nghia Doan, Seyyed Ali Hashemi, Marco Mondelli, Warren J. Gross |
| 2018 | ISIT | A New Coding Paradigm for the Primitive Relay Channel. | Marco Mondelli, S. Hamed Hassani, Rdiger L. Urbanke |
| 2018 | ITW | Binary Linear Codes with Optimal Scaling: Polar Codes with Large Kernels. | Arman Fazeli, S. Hamed Hassani, Marco Mondelli, Alexander Vardy |
| 2017 | GLOBECOM | Partitioned List Decoding of Polar Codes: Analysis and Improvement of Finite Length Performance. | Seyyed Ali Hashemi, Marco Mondelli, S. Hamed Hassani, Rdiger L. Urbanke, Warren J. Gross |
| 2017 | ISIT | Construction of polar codes with sublinear complexity. | Marco Mondelli, S. Hamed Hassani, Rdiger L. Urbanke |
| 2017 | WCNC | Capacity-Achieving Rate-Compatible Polar Codes for General Channels. | Marco Mondelli, S. Hamed Hassani, Ivana Maric, Dennis Hui, Song-Nam Hong |
| 2016 | ISIT | Comparing the bit-MAP and block-MAP decoding thresholds of reed-muller codes on BMS channels. | Shrinivas Kudekar, Santhosh Kumar, Marco Mondelli, Henry D. Pfister, Rdiger L. Urbanke |
| 2016 | STOC | Reed-Muller codes achieve capacity on erasure channels. | Shrinivas Kudekar, Santhosh Kumar, Marco Mondelli, Henry D. Pfister, Eren Sasoglu, Rdiger L. Urbanke |
| 2015 | ISIT | Unified scaling of polar codes: Error exponent, scaling exponent, moderate deviations, and error floors. | Marco Mondelli, Rdiger L. Urbanke, Seyed Hamed Hassani |
| 2014 | ISIT | From polar to Reed-Muller codes: A technique to improve the finite-length performance. | Marco Mondelli, Seyed Hamed Hassani, Rdiger L. Urbanke |
| 2014 | ISIT | Achieving Marton's region for broadcast channels using polar codes. | Marco Mondelli, Seyed Hamed Hassani, Rdiger L. Urbanke, Igal Sason |
| 2013 | ITW | Scaling exponent of list decoders with applications to polar codes. | Marco Mondelli, Seyed Hamed Hassani, Rdiger L. Urbanke |
| 2012 | ICASSP | A cooperative approach for amplify-and-forward differential transmitted reference IR-UWB relay systems. | Marco Mondelli, Qi Zhou, Xiaoli Ma, Vincenzo Lottici |