Marco Mondelli

Orcid: 0000-0002-3242-7020

According to our database1, Marco Mondelli authored at least 67 papers between 2011 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Average gradient outer product as a mechanism for deep neural collapse.
CoRR, 2024

Contraction of Markovian Operators in Orlicz Spaces and Error Bounds for Markov Chain Monte Carlo.
CoRR, 2024

Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth.
CoRR, 2024

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features.
CoRR, 2024

2023
Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence.
Trans. Mach. Learn. Res., 2023

Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing.
CoRR, 2023

Improved Convergence of Score-Based Diffusion Models via Prediction-Correction.
CoRR, 2023

Stability, Generalization and Privacy: Precise Analysis for Random and NTK Features.
CoRR, 2023

Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Models.
Proceedings of the IEEE Information Theory Workshop, 2023

Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise.
Proceedings of the IEEE International Symposium on Information Theory, 2023

Concentration without Independence via Information Measures.
Proceedings of the IEEE International Symposium on Information Theory, 2023

Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods.
Proceedings of the International Conference on Machine Learning, 2023

Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels.
Proceedings of the International Conference on Machine Learning, 2023

2022
Parallelism Versus Latency in Simplified Successive-Cancellation Decoding of Polar Codes.
IEEE Trans. Wirel. Commun., 2022

Decoding Reed-Muller Codes With Successive Codeword Permutations.
IEEE Trans. Commun., 2022

Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks.
J. Mach. Learn. Res., 2022

Optimal Combination of Linear and Spectral Estimators for Generalized Linear Models.
Found. Comput. Math., 2022

Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods.
CoRR, 2022

Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models.
CoRR, 2022

Finite Sample Identification of Wide Shallow Neural Networks with Biases.
CoRR, 2022

Bayes-optimal limits in structured PCA, and how to reach them.
CoRR, 2022

Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Sharp asymptotics on the compression of two-layer neural networks.
Proceedings of the IEEE Information Theory Workshop, 2022

Polar Coded Computing: The Role of the Scaling Exponent.
Proceedings of the IEEE International Symposium on Information Theory, 2022

Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing.
Proceedings of the International Conference on Machine Learning, 2022

2021
Sublinear Latency for Simplified Successive Cancellation Decoding of Polar Codes.
IEEE Trans. Wirel. Commun., 2021

Binary Linear Codes With Optimal Scaling: Polar Codes With Large Kernels.
IEEE Trans. Inf. Theory, 2021

Decoding Reed-Muller Codes with Successive Factor-Graph Permutations.
CoRR, 2021

On Connectivity of Solutions in Deep Learning: The Role of Over-parameterization and Feature Quality.
CoRR, 2021

When Are Solutions Connected in Deep Networks?
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

PCA Initialization for Approximate Message Passing in Rotationally Invariant Models.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sparse Multi-Decoder Recursive Projection Aggregation for Reed-Muller Codes.
Proceedings of the IEEE International Symposium on Information Theory, 2021

Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks.
Proceedings of the 38th International Conference on Machine Learning, 2021

Approximate Message Passing with Spectral Initialization for Generalized Linear Models.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Successive Syndrome-Check Decoding of Polar Codes.
Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, 2021

2020
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Simplified Successive Cancellation Decoding of Polar Codes Has Sublinear Latency.
Proceedings of the IEEE International Symposium on Information Theory, 2020

Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks.
Proceedings of the 37th International Conference on Machine Learning, 2020

2019
Rate-Flexible Fast Polar Decoders.
IEEE Trans. Signal Process., 2019

Construction of Polar Codes With Sublinear Complexity.
IEEE Trans. Inf. Theory, 2019

Fundamental Limits of Weak Recovery with Applications to Phase Retrieval.
Found. Comput. Math., 2019

Analysis of a Two-Layer Neural Network via Displacement Convexity.
CoRR, 2019

A New Coding Paradigm for the Primitive Relay Channel.
Algorithms, 2019

On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018
How to Achieve the Capacity of Asymmetric Channels.
IEEE Trans. Inf. Theory, 2018

Decoder Partitioning: Towards Practical List Decoding of Polar Codes.
IEEE Trans. Commun., 2018

On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition.
CoRR, 2018

Decoding Reed-Muller and Polar Codes by Successive Factor Graph Permutations.
Proceedings of the 10th IEEE International Symposium on Turbo Codes & Iterative Information Processing, 2018

On the Decoding of Polar Codes on Permuted Factor Graphs.
Proceedings of the IEEE Global Communications Conference, 2018

2017
Reed-Muller Codes Achieve Capacity on Erasure Channels.
IEEE Trans. Inf. Theory, 2017

Binary Linear Codes with Optimal Scaling and Quasi-Linear Complexity.
CoRR, 2017

Capacity-Achieving Rate-Compatible Polar Codes for General Channels.
Proceedings of the 2017 IEEE Wireless Communications and Networking Conference Workshops, 2017

Partitioned List Decoding of Polar Codes: Analysis and Improvement of Finite Length Performance.
Proceedings of the 2017 IEEE Global Communications Conference, 2017

2016
From Polar to Reed-Muller Codes - Unified Scaling, Non-standard Channels, and a Proven Conjecture.
PhD thesis, 2016

Unified Scaling of Polar Codes: Error Exponent, Scaling Exponent, Moderate Deviations, and Error Floors.
IEEE Trans. Inf. Theory, 2016

Comparing the bit-MAP and block-MAP decoding thresholds of reed-muller codes on BMS channels.
Proceedings of the IEEE International Symposium on Information Theory, 2016

2015
Scaling Exponent of List Decoders With Applications to Polar Codes.
IEEE Trans. Inf. Theory, 2015

Achieving Marton's Region for Broadcast Channels Using Polar Codes.
IEEE Trans. Inf. Theory, 2015

Reed-Muller Codes Achieve Capacity on the Binary Erasure Channel under MAP Decoding.
CoRR, 2015

2014
Joint Power Allocation and Path Selection for Multi-Hop Noncoherent Decode and Forward UWB Communications.
IEEE Trans. Wirel. Commun., 2014

From Polar to Reed-Muller Codes: A Technique to Improve the Finite-Length Performance.
IEEE Trans. Commun., 2014

Achieving the Superposition and Binning Regions for Broadcast Channels Using Polar Codes.
CoRR, 2014

2013
A Finite Difference Scheme for the Stack Filter Simulating the MCM.
Image Process. Line, 2013

2012
A cooperative approach for amplify-and-forward differential transmitted reference IR-UWB relay systems.
Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011
Finite Difference Schemes for MCM and AMSS.
Image Process. Line, 2011


  Loading...