Get started
Author

Pierfrancesco Beneventano

Observed name: Beneventano, Pierfrancesco
OpenAlex ID: A5040473476
Models with higher effective dimensions tend to produce more uncertain estimates
2022 · Arnald Puy, Pierfrancesco Beneventano, et al. · Science Advances · 70
PDF
Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
2024 · Andreyev, Arseniy, Beneventano, Pierfrancesco · arXiv (Cornell University) · 34
PDF
On the Trajectories of SGD Without Replacement
2023 · Beneventano, Pierfrancesco · arXiv (Cornell University) · 17
PDF
High-dimensional approximation spaces of artificial neural networks and applications to partial differential equations
2020 · Beneventano, Pierfrancesco, Cheridito, Patrick, et al. · arXiv (Cornell University) · 14
PDF
Deep neural network approximation theory for high-dimensional functions
2021 · Beneventano, Pierfrancesco, Cheridito, Patrick, et al. · arXiv (Cornell University) · 13
PDF
Momentum Further Constrains Sharpness at the Edge of Stochastic Stability
2026 · Andreyev, Arseniy, Ananthkumar, Advikar, et al. · arXiv (Cornell University) · 7
PDF
Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
2025 · Beneventano, Pierfrancesco, Woodworth, Blake · arXiv (Cornell University) · 5
PDF
How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD
2024 · Beneventano, Pierfrancesco, Pinto, Andrea, et al. · arXiv (Cornell University) · 5
PDF
The Spectral Dynamics and Noise Geometry of Muon
2026 · Beneventano, Pierfrancesco, Abdelmoneum, Mahmoud, et al. · arXiv (Cornell University) · 4
PDF
Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model
2026 · Xu, Yizhou, Beneventano, Pierfrancesco, et al. · arXiv (Cornell University) · 4
PDF
Inference-Time Amplification of Weak Reasoning Models
2026 · Sunkaraneni, Varun, Beneventano, Pierfrancesco, et al. · arXiv (Cornell University) · 3
PDF
pAI/MSc: ML Theory Research with Humans on the Loop
2026 · Abdelmoneum, Mahmoud, Beneventano, Pierfrancesco, et al. · arXiv (Cornell University) · 2
PDF
Too Sharp, Too Sure: When Calibration Follows Curvature
2026 · Morosini, Alessandro, Gjika, Matea, et al. · arXiv (Cornell University) · 2
PDF
Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure
2026 · Bottino, Federico, Ferrero, Carlo, et al. · arXiv (Cornell University) · 2
PDF
Does Weight Decay Enhance Training Stability?
2026 · Saether, Marius, Kolic, Amir, et al. · arXiv (Cornell University) · 1
PDF
Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization
2026 · Torti, Leonardo, Rimoldi, Emanuele, et al. · arXiv (Cornell University)
PDF
Edge of Stability Selectively Shapes Learning Across the Data Distribution
2026 · Kwag, Shauna, Ganesh, Anakha, et al. · arXiv (Cornell University)
PDF
Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
2026 · Das, Mohua, Beneventano, Pierfrancesco, et al. · arXiv (Cornell University)
PDF
Distribution-Aware Programming: Learning Specialized Solvers from Experience
2026 · Koganti, Saharsh, Mishra, Priyadarsi, et al. · arXiv (Cornell University)
PDF
Same Error, Different Function: The Optimizer as an Implicit Prior in Financial Time Series
2026 · Cortesi, Federico Vittorio, Iannone, Giuseppe, et al. · arXiv (Cornell University)
PDF
Works count: 20
Citation count: 183
H-index: 6
I10-index: 5
Year
Topic
Type