Pierfrancesco Urbani

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 17

Top Topics

Alternating Least Squares

Gaussian Mixture

Low Dimensional

Top Venues

Mach. Learn. Sci. Technol.

Publications

Samantha J. Fournier, Pierfrancesco Urbani
Generative modeling through internal high-dimensional chaotic activity. CoRR (2024)
Persia Jana Kamali, Pierfrancesco Urbani
Stochastic Gradient Descent outperforms Gradient Descent in recovering a high-dimensional signal in a glassy energy landscape. CoRR (2023)
Francesca Mignacco, Pierfrancesco Urbani, Lenka Zdeborová
Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem. CoRR (2021)
Stefano Sarao Mannelli, Pierfrancesco Urbani
Just a Momentum: Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problem. CoRR (2021)
Francesca Mignacco, Pierfrancesco Urbani, Lenka Zdeborová
Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem. Mach. Learn. Sci. Technol. 2 (3) (2021)
Stefano Sarao Mannelli, Pierfrancesco Urbani
Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems. NeurIPS (2021)
Francesca Mignacco, Pierfrancesco Urbani
The effective noise of Stochastic Gradient Descent. CoRR (2021)
Francesca Mignacco, Florent Krzakala, Yue Lu, Pierfrancesco Urbani, Lenka Zdeborová
The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture. ICML (2020)
Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval. NeurIPS (2020)
Francesca Mignacco, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification. NeurIPS (2020)
Francesca Mignacco, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification. CoRR (2020)
Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval. CoRR (2020)
Stefano Sarao Mannelli, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Passed & Spurious: analysing descent algorithms and local minima in spiked matrix-tensor model. CoRR (2019)
Stefano Sarao Mannelli, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models. ICML (2019)
Fabrizio Antenucci, Silvio Franz, Pierfrancesco Urbani, Lenka Zdeborová
On the glassy nature of the hard phase in inference problems. CoRR (2018)
Fabrizio Antenucci, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Approximate Survey Propagation for Statistical Inference. CoRR (2018)
Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Marvels and Pitfalls of the Langevin Algorithm in Noisy High-dimensional Inference. CoRR (2018)