ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Marco Mondelli

Marco Mondelli

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 3:00 AM AMS

14

papers

257

total citations

papers (14)

Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology

NEURIPS 2020arXiv

Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model

NEURIPS 2023arXiv

Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization

NEURIPS 2022arXiv

PCA Initialization for Approximate Message Passing in Rotationally Invariant Models

NEURIPS 2021arXiv

The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?

NEURIPS 2022arXiv

High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws

Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse

When Are Solutions Connected in Deep Networks?

NEURIPS 2021arXiv

How Spurious Features are Memorized: Precise Analysis for Random and NTK Features

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features

Test-Time Training Provably Improves Transformers as In-context Learners

Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers

NEURIPS 2025arXiv

Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth